Search

Multitemporal cross-sensor imagery is fundamental for the monitoring of the Earth’s surface over time. However, these data often lack visual consistency because of variations in the atmospheric and surface conditions, making it challenging to compare and analyze images. Various image-normalization methods have been proposed to address this issue, such as histogram matching and linear regression using iteratively reweighted multivariate alteration detection (IR-MAD). However, these methods have limitations in their ability to maintain important features and their requirement of reference images, which may not be available or may not adequately represent the target images. To overcome these limitations, a relaxation-based algorithm for satellite-image normalization is proposed. The algorithm iteratively adjusts the radiometric values of images by updating the normalization parameters (slope (α) and intercept (β)) until a desired level of consistency is reached. This method was tested on multitemporal cross-sensor-image datasets and showed significant improvements in radiometric consistency compared to other methods. The proposed relaxation algorithm outperformed IR-MAD and the original images in reducing radiometric inconsistencies, maintaining important features, and improving the accuracy (MAE = 2.3; RMSE = 2.8) and consistency of the surface-reflectance values (R2 = 87.56%; Euclidean distance = 2.11; spectral angle mapper = 12.60).

Optical character recognition (OCR) in images captured from arbitrary angles requires preliminary normalization, i.e. a geometric transformation resulting in an image as if it was captured at an angle suitable for OCR. In most cases, a surface containing characters can be considered flat, and a pinhole model can be adopted for a camera. Thus, in theory, the normalization should be projective. Usually, the camera optical axis is approximately perpendicular to the document surface, so the projective normalization can be replaced with an affine one without a significant loss of accuracy. An affine image transformation is performed significantly faster than a projective normalization, which is important for OCR on mobile devices. In this work, we propose a fast approach for image normalization. It utilizes an affine normalization instead of a projective one if there is no significant loss of accuracy. The approach is based on a proposed criterion for the normalization accuracy: root mean square (RMS) coordinate discrepancies over the region of interest (ROI). The problem of optimal affine normalization according to this criterion is considered. We have established that this unconstrained optimization is quadratic and can be reduced to a problem of fractional quadratic functions integration over the ROI. The latter was solved analytically in the case of OCR where the ROI consists of rectangles. The proposed approach is generalized for various cases when instead of the affine transform its special cases are used: scaling, translation, shearing, and their superposition, allowing the image normalization procedure to be further accelerated.

Translation rotation and scale invariants of Tchebichef moments are commonly used descriptors in image analysis. Existing invariant algorithms either indirectly compute from geometric moments or directly using Tchebichef moments. The former approach is relatively simple, but inefficient, especially when the system consists only of Tchebichef moments. Likewise, the latter approach is complicated, mainly because of the method used to formulate the invariant algorithm. Hence, in this paper, we introduce a new set of translation, rotation and scale Tchebichef moment invariants (TRSI) using moment normalization, which is much computationally efficient and accurate. This is achieved by formulating the recurrence relationship of the descriptors and successfully resolve uniqueness issues of principal axis normalization. Experimental studies show that the proposed method is computationally much faster and possesses higher discriminative power in classification when compared with present invariant algorithms. The main contribution of this paper is a novel fast computational algorithm that simplifies translation, rotation and scale invariant algorithms of Tchebichef moments and a novel normalization scheme that preserve invariants’ orthogonality from the moment functions. The technique can be deployed to derive affine invariants of Tchebichef moments, and invariants for other orthogonal moments like Krawtchouk, Hahn, Racah moments etc.

CNC display (Computer Numerical Control)is an important source of information on industrial production equipment operation (e.g., it shows errors in real-time). In this paper, we consider the direct monitoring problem for a CNC display to automatically detect error codes and analyze their sequences. We present our pilot service implementation, which uses real-life production equipmenta VARIA machine with CNC SINUMERIK 840D sl system.

The star identification (star-ID) algorithm can match the stars captured by an optical system with a star catalog according to certain features. Star-ID has been an important research issue in many astronomical studies and a strong robust star-ID algorithm can effectively identify a certain number of stars as a standard source to correct uncalibrated telescopes. Generally, before star-ID, the celestial coordinates should be translated into the image coordinates with knowledge of optical center coordinates, image rotation angle, focal length of optical system, image sensor's pixel size and so on. For an uncalibrated telescope, the star-ID performance usually suffers from the errors or even the lack of these parameters. In this paper, a novel star-ID algorithm is devised which is based on image normalization technique and the Zernike moment such that the invariant features of asterisms are extracted instead of traditional ways. And three real images which captured via an uncalibrated ground-based telescope are used to validate our method, and the results show that it can effectively identify stars with a success rate of 99.27%, which demonstrate the robustness and accuracy of the proposed method.

Primary Central Nervous System Lymphoma (PCNSL) is an aggressive neoplasm with a poor prognosis. Although therapeutic progresses have significantly improved Overall Survival (OS), a number of patients do not respond to HD–MTX-based chemotherapy (15–25%) or experience relapse (25–50%) after an initial response. The reasons underlying this poor response to therapy are unknown. Thus, there is an urgent need to develop improved predictive models for PCNSL. In this study, we investigated whether radiomics features can improve outcome prediction in patients with PCNSL. A total of 80 patients diagnosed with PCNSL were enrolled. A patient sub-group, with complete Magnetic Resonance Imaging (MRI) series, were selected for the stratification analysis. Following radiomics feature extraction and selection, different Machine Learning (ML) models were tested for OS and Progression-free Survival (PFS) prediction. To assess the stability of the selected features, images from 23 patients scanned at three different time points were used to compute the Interclass Correlation Coefficient (ICC) and to evaluate the reproducibility of each feature for both original and normalized images. Features extracted from Z-score normalized images were significantly more stable than those extracted from non-normalized images with an improvement of about 38% on average (p-value < 10−12). The area under the ROC curve (AUC) showed that radiomics-based prediction overcame prediction based on current clinical prognostic factors with an improvement of 23% for OS and 50% for PFS, respectively. These results indicate that radiomics features extracted from normalized MR images can improve prognosis stratification of PCNSL patients and pave the way for further study on its potential role to drive treatment choice.

This work was sponsored in part by the Agencia Es-tatal de Investigacion under project PID2019-105142RB-C22/AEI/10.13039/50110 0 011033, Junta de Andalucia under project PY20_00286,and the work by Fernando Perez-Bueno was spon-sored by Ministerio de Economia, Industria y Competitividad un-der FPI contract BES-2017-081584. Funding for open access charge: Universidad de Granada/CBUA., Background and Objective: Color variations in digital histopathology severely impact the performance of computer-aided diagnosis systems. They are due to differences in the staining process and acquisition system, among other reasons. Blind color deconvolution techniques separate multi-stained images into single stained bands which, once normalized, can be used to eliminate these negative color variations and improve the performance of machine learning tasks. Methods: In this work, we decompose the observed RGB image in its hematoxylin and eosin components. We apply Bayesian modeling and inference based on the use of Super Gaussian sparse priors for each stain together with prior closeness to a given reference color-vector matrix. The hematoxylin and eosin components are then used for image normalization and classification of histological images. The proposed framework is tested on stain separation, image normalization, and cancer classification problems. The results are measured using the peak signal to noise ratio, normalized median intensity and the area under ROC curve on five different databases. Results: The obtained results show the superiority of our approach to current state-of-the-art blind color deconvolution techniques. In particular, the fidelity to the tissue improves 1,27 dB in mean PSNR. The normalized median intensity shows a good normalization quality of the proposed approach on the tested datasets. Finally, in cancer classification experiments the area under the ROC curve improves from 0.9491 to 0.9656 and from 0.9279 to 0.9541 on Camelyon-16 and Camelyon-17, respectively, when the original and processed images are used. Furthermore, these figures of merits are better than those obtained by the methods compared with. Conclusions: The proposed framework for blind color deconvolution, normalization and classification of images guarantees fidelity to the tissue structure and can be used both for normalization and classification. In addition, color deconvolution enables the use of the optical density space for classification, which improves the classification performance., Agencia Es-tatal de Investigacion PID2019-105142RB-C22/AEI/10.13039/50110 0 011033, Junta de Andalucia PY20_00286, Ministerio de Economia, Industria y Competitividad under FPI BES-2017-081584, Universidad de Granada/CBUA

Orientador: Rubens Augusto Camargo Lamparelli Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Agricola Resumo: Estudos e pesquisas referentes ao acompanhamento da produção agropecuária têm um peso determinante e estratégico na economia do país. Nos últimos anos, essas pesquisas vêm sofrendo grandes transformações para se tornarem menos subjetivas. A associação das técnicas de sensoriamento remoto e métodos estatísticos podem proporcionar uma visão sinóptica das áreas semeadas, gerando, assim informações sobre a área plantada das culturas e a variabilidade existente nelas. Entretanto, a utilização dos dados provenientes de imagens de satélites está condicionada, principalmente, às propriedades de refletância e absorção dos componentes da superfície e pelo comportamento da atmosfera. Dentre as culturas de grande valor econômico, a soja (Glycine max (L) Merrill.) se destaca como um dos principais produtos da agricultura brasileira, assumindo grande importância econômica nas exportações. O estado do Paraná se destaca como um dos maiores produtores agrícolas do país, e a sua economia é baseada principalmente na agricultura voltada para a produção de grãos. Neste contexto, o objetivo da pesquisa foi estudar a relação entre o comportamento espectral da cultura de soja com a ao longo de seu ciclo de desenvolvimento, gerando informações e metodologias para auxiliar no acompanhamento da produção e estimativa de área da cultura na região Oeste do Paraná. As áreas monitoradas abrangem 36 municípios e duas áreas agrícolas comerciais localizadas próximas ao município de Cascavel/PR. Foram utilizadas imagens do satélite Landsat 5/TM (cena órbita/ponto 223/77) e imagens do satélite Terra sensor MODIS (produto MOD13Q1), caracterizando, assim, a passagem de escala entre as imagens dos dois sensores com resoluções espaciais diferentes. Dados de produtividade da cultura foram coletados nas escalas local (para as duas áreas monitoradas) e regional junto à Secretária de Agricultura e Abastecimento do Paraná ¿ SEAB (para os 36 municípios). A cultura da soja foi monitorada nas safras 2003/2004 e 2004/2005 utilizando imagens dos satélites. Para a utilização das imagens do satélite Landsat 5/TM de forma multitemporal foram realizados ainda os procedimentos de correção atmosférica e normalização de imagens. No intuito de caracterizar a resposta espectral da biomassa da cultura da soja e a sua relação com a produtividade final, geraram-se imagens referentes aos índices de vegetação NDVI e GVI. Foram realizadas análises de correlação e regressão entre dados de produtividade (variável predita) e dados espectrais (variável preditora) oriundos dos índices de vegetação (NDVI e GVI) em nível municipal (36 municípios) e local (duas áreas). Os resultados obtidos com a correção atmosférica e a normalização de imagens são coerentes quanto ao comportamento espectral dos alvos, vegetação e solo. Após o mapeamento das áreas com a cultura da soja (¿máscaras de soja¿), por meio das imagens temporais do Landsat 5/TM, foi possível realizar a passagem de escala para o sensor MODIS. O comportamento espectral da cultura se mostrou diferente para as imagens Landsat 5/TM com os tratamentos de refletância aparente, de superfície e de normalização. Por meio dos gráficos dos perfis espectrais traduzidos pelos índices NDVI e GVI foi possível acompanhar o ciclo de desenvolvimento da cultura da soja. As melhores correlações e regressões lineares entre os parâmetros espectrais e a produtividade final ocorreram quando considerado todo o ciclo de desenvolvimento da cultura. Quanto aos índices de vegetação utilizados NDVI e GVI, observou-se que o GVI teve comportamento com menor variação quando analisado os resultados das regressões. Em síntese, os resultados demonstraram que utilizando somente técnicas de modelagem estatística com dados espectrais foi possível estimar em até 85% a variabilidade encontrada na produtividade da soja Abstract: Studies and researches referring to attendance of the agropecuary production have a determinant strategic importance in the economy of the country. In the last years, those researches have been suffering great transformations to become less subjectives. The association of the remote sensing technique and statistic methods can provide a synoptic view of the seeded areas, in this manner producing information about the planted area of the crops and the variability on them. However, the use of data from the images of satellite is stipulated mainly to the reflectivity properties and absorption of the surface components and also for the atmosphere behaviour. Amongst the crops of great economic value, the soybean (Glycine max (L) Merrill.) emphasizes as one of the main product of the Brazilian agriculture, assuming big economic importance in the exportations. The Paraná state stands out as one of the biggest agricultural producers of the country, and its economy is based mainly towards to the production of grains. In this context, the aim of the research was study the relation between the spectral behaviour of the soybean crop with the end yield along its development cycle, producing information and methodologies to assist the attendance of the production and area estimation of the western Paraná region crop. The areas monitored reach 36 municipal districts and two agricultural commercial areas located near of Cascavel/PR. It was used images from satellite Landsat 5/TM (orbit/point 223/77) and images of the satellite Terra sensor MODIS (product MOD13Q1), then characterizing the crossing scale between the images from both sensors with different spatial resolution. Crop yield data were collected, in the local scale (to both monitored areas) and in the regional scale together with the Secretary of Agriculture (SEAB) (to the 36 municipal districts). Through the satellites images, the soybean crop was monitored in the 2003/2004 and 2004/2005 harvests. For the use of images from the satellite Landsat 5/TM of multitemporal form was realized the proceeding of atmospheric correction and image normalization. In the aim of distinguishing the biomass spectral answer of the soybean crop and its relation to the end yield, it was created images referring to vegetation indexes NDVI and GVI. It was accomplished analyses of correlation and regression between the yield data (variable predict) and spectral data (variable predictor) derived from vegetation indexes (NDVI and GVI) in municipal level (36 municipal districts) and local (two areas). The results obtained with the atmospheric correction and image normalization presented coherent as to the spectral behaviour of the vegetation and soil target. After the area mapping with the soybean crop (soybean mask) by the temporary images of Landsat 5/TM, it was possible to realize the cross-scale to the MODIS sensor. The spectral behaviour of the crop was showed different in the Landsat 5/TM images to the apparent reflectance usage, surface and normalization. By mean of the graphics of spectral profile translated from the NDVI and GVI indexes was possible follow the development cycle of the soybean crop. The best correlations and linear regressions between the spectral parameters and the end yield will occur when it is considered all the cycle of the crop development. For the matters of vegetation indexes NDVI and GVI used, it was observed that the GVI had a less variable behaviour when analysed the results of regressions. In the sum up, the results showed that using only statistical modelling techniques with spectral data was possible estimate 85% of variability found in the soybean yield Doutorado Planejamento e Desenvolvimento Rural Sustentável Doutor em Engenharia Agrícola

BackgroundPrevious histopathology and MRI studies have addressed the differences between focal white matter lesions (FWML) and diffusely abnormal white matter (DAWM) in multiple sclerosis (MS). These two categories of white matter T2-weighted (T2w) hyperintensity show different degrees of demyelination, axonal loss and immune cell density on histopathology, potentially offering distinct correlations with symptoms.Objectives1) To automate the separation of FWML and DAWM using T2w MRI intensity thresholds and to investigate their differences in magnetization transfer ratios (MTR), which are sensitive to myelin content; 2) to correlate MTR values in FWML and DAWM with normalized signal intensity values on fluid attenuated inversion recovery (FLAIR), T2w, and T1-weighted (T1w) contrasts, as well as with the ratio of T2w/T1w normalized values, in order to determine whether these normalized intensities can be used as myelin-sensitive markers when MTR is not available.MethodsUsing similar 3T MRI protocols, 2 MS cohorts of 20 participants each were scanned in 2 centers, including: 3D T1w (MP2RAGE), 3D FLAIR, 2D T2w, and 3D magnetization-transfer (MT) contrasts. We used the first dataset to develop an automated technique to separate FWML from DAWM and the second one to validate the automation of the technique. We applied the automatic thresholds to both datasets and assessed the overlap of the manual and the automated masks using Dice kappa. We also assessed differences in mean MTR values between NAWM, DAWM and FWML, using manually and automatically derived masks in both datasets. Finally, we used the mean intensity of manually-traced areas of NAWM on T2w images as the normalization factor for each MRI contrast, and compared these with the normalized-intensity values obtained using automated NAWM (A-NAWM) masks as the normalization factor. Paired t-tests assessed the MTR differences across tissue types. Wilcoxon Signed Rank test and paired t-tests assessed FWML and DAWM differences in manual and automated derived volumes. Pearson correlations assessed the relationship between MTR and normalized intensity values in the manual and automated derived masks.ResultsThe mean Dice-kappa values for dataset 1 were: 0.8 for DAWM masks and 0.7 for FWML masks. In dataset 2, mean dice-kappa values were: 0.8 for DAWM and 0.8 for FWML. Also, manual and automated DAWM and FWML volumes were not significantly different in both datasets. MTR values (expressed as mean and standard deviation, arbitrary units) were significantly lower in manually derived FWML compared with DAWM in both datasets: 1) FWML: 37.1 ± 3.2 vs DAWM: 43.3 ± 2.1; t=13.2; pIn both datasets, manually derived FWML and DAWM MTR values showed significant correlations with normalized FLAIR (r=−0.35 to −0.67; p=0.06 to ConclusionsThe separation of FWML and DAWM on MRI scans of MS patients using automated intensity thresholds on T2w images is feasible. MTR values are significantly lower in FWML than DAWM, and DAWM values are significantly lower than NAWM, reflecting potentially greater demyelination within focal lesions. Normalized intensity values of different MRI contrasts exhibit a significant correlation with MTR values in both tissues of interest and could be used as a proxy to assess demyelination when MTR images are not available.

Illumination variations in non-atmospherically corrected high-resolution satellite (HRS) images acquired at different dates/times/locations pose a major challenge for large-area environmental mapping and monitoring. This problem is exacerbated in cases where a classification model is trained only on one image (and often limited training data) but applied to other scenes without collecting additional samples from these new images. In this research, by focusing on caribou lichen mapping, we evaluated the potential of using conditional Generative Adversarial Networks (cGANs) for the normalization of WorldView-2 (WV2) images of one area to a source WV2 image of another area on which a lichen detector model was trained. In this regard, we considered an extreme case where the classifier was not fine-tuned on the normalized images. We tested two main scenarios to normalize four target WV2 images to a source 50 cm pansharpened WV2 image: (1) normalizing based only on the WV2 panchromatic band, and (2) normalizing based on the WV2 panchromatic band and Sentinel-2 surface reflectance (SR) imagery. Our experiments showed that normalizing even based only on the WV2 panchromatic band led to a significant lichen-detection accuracy improvement compared to the use of original pansharpened target images. However, we found that conditioning the cGAN on both the WV2 panchromatic band and auxiliary information (in this case, Sentinel-2 SR imagery) further improved normalization and the subsequent classification results due to adding a more invariant source of information. Our experiments showed that, using only the panchromatic band, F1-score values ranged from 54% to 88%, while using the fused panchromatic and SR, F1-score values ranged from 75% to 91%.

Many research applications of neuroimaging use magnetic resonance imaging (MRI). As such, recommendations for image analysis and standardized imaging pipelines exist. Clinical imaging, however, relies heavily on X-ray computed tomography (CT) scans for diagnosis and prognosis. Currently, there is only one image processing pipeline for head CT, which focuses mainly on head CT data with lesions. We present tools and a complete pipeline for processing CT data, focusing on open-source solutions, that focus on head CT but are applicable to most CT analyses. We describe going from raw DICOM data to a spatially normalized brain within CT presenting a full example with code. Overall, we recommend anonymizing data with Clinical Trials Processor, converting DICOM data to NIfTI using dcm2niix, using BET for brain extraction, and registration using a publicly-available CT template for analysis.

Background Analysis of heterogeneous populations such as viral quasispecies is one of the most challenging bioinformatics problems. Although machine learning models are becoming to be widely employed for analysis of sequence data from such populations, their straightforward application is impeded by multiple challenges associated with technological limitations and biases, difficulty of selection of relevant features and need to compare genomic datasets of different sizes and structures. Results We propose a novel preprocessing approach to transform irregular genomic data into normalized image data. Such representation allows to restate the problems of classification and comparison of heterogeneous populations as image classification problems which can be solved using variety of available machine learning tools. We then apply the proposed approach to two important problems in molecular epidemiology: inference of viral infection stage and detection of viral transmission clusters using next-generation sequencing data. The infection staging method has been applied to HCV HVR1 samples collected from 108 recently and 257 chronically infected individuals. The SVM-based image classification approach achieved more than 95% accuracy for both recently and chronically HCV-infected individuals. Clustering has been performed on the data collected from 33 epidemiologically curated outbreaks, yielding more than 97% accuracy. Conclusions Sequence image normalization method allows for a robust conversion of genomic data into numerical data and overcomes several issues associated with employing machine learning methods to viral populations. Image data also help in the visualization of genomic data. Experimental results demonstrate that the proposed method can be successfully applied to different problems in molecular epidemiology and surveillance of viral diseases. Simple binary classifiers and clustering techniques applied to the image data are equally or more accurate than other models.

Объектом исследования является набор из 1000 изображений листьев пшеницы. Цель работы – разработка и реализация программы для получения надежного распознавания 10-ти Ð¾ÑÐ½Ð¾Ð²Ð½Ñ‹Ñ Ð²Ð¸Ð´Ð¾Ð² болезней пшеницы на Ð¸Ð·Ð¾Ð±Ñ€Ð°Ð¶ÐµÐ½Ð¸ÑÑ . Рассмотрены существующие методы и предложен метод цифровой обработки изображений для диагностики болезней растений по цифровым RGB-фотоизображениям листьев в видимом спектре при использовании матрицы GLCM, сравнения Ð¿Ð¾Ð»ÑƒÑ‡ÐµÐ½Ð½Ñ‹Ñ ÑÑ‚Ð°Ð»Ð¾Ð½Ð½Ñ‹Ñ Ð¾Ð¿Ð¸ÑÐ°Ð½Ð¸Ð¹ Ð¼Ð°Ñ‚ÐµÐ¼Ð°Ñ‚Ð¸Ñ‡ÐµÑÐºÐ¸Ñ Ð¾Ð¶Ð¸Ð´Ð°Ð½Ð¸Ð¹ по максимуму функции принадлежности, а также последующего распознавания тестовой выборки на основе бинаризации результатов и мажоритарного голосования. Проведено математическое моделирование предложенного метода, разработан и реализован классификатор для определения вида болезни листьев пшеницы. Новизна работы заключается в способе компьютерной диагностики Ð²Ð¸Ð´Ð¸Ð¼Ñ‹Ñ ÑÐ¸Ð¼Ð¿Ñ‚Ð¾Ð¼Ð¾Ð² заболеваний листьев растений по фотоизображениям посредством оперирования матрицей GLCM и интерпретировании результатов, используя нечеткую логику. Предложенный Ð¿Ð¾Ð´Ñ Ð¾Ð´ при группировке по 25-ти изображениям позволяет получить достоверное распознавание в более чем 90% ÑÐ»ÑƒÑ‡Ð°ÑÑ . В перспективе, разработанное ПО имеет все шансы на внедрение в автономные БПЛА для автоматического распознавания Ð¿Ð¾Ð²Ñ€ÐµÐ¶Ð´ÐµÐ½Ð½Ñ‹Ñ Ð¿Ð°Ñ‚Ð¾Ð»Ð¾Ð³Ð¸ÑÐ¼Ð¸ площадей, Ð·Ð°ÑÐµÑÐ½Ð½Ñ‹Ñ Ñ€Ð°Ð·Ð»Ð¸Ñ‡Ð½Ñ‹Ð¼Ð¸ культурными растениями. Успешная интеграция разработанного ПО в сельское Ñ Ð¾Ð·ÑÐ¹ÑÑ‚Ð²Ð¾ позволит снизить физическую нагрузку с фермеров, позволит вовремя диагностировать начинающиеся очаги болезней ÐºÑƒÐ»ÑŒÑ‚ÑƒÑ€Ð½Ñ‹Ñ Ñ€Ð°ÑÑ‚ÐµÐ½Ð¸Ð¹, после устранения ÐºÐ¾Ñ‚Ð¾Ñ€Ñ‹Ñ Ð¿Ð¾Ð²Ñ‹ÑÐ¸Ñ‚ÑÑ урожайность., The object of study is a dataset of 1000 images of wheat leaves. The main goal of the work was the development and implementation of software for obtaining reliable recognition of the 10 main types of wheat diseases in the images. Existing methods are explored and a digital image processing method is proposed for diagnosing plant diseases using digital RGB photographic images of leaves in visible spectrum using the GLCM matrix, comparing the results of mathematical expectations for the maximum functions inherent in subsequent voting recognition. A mathematical modeling of the proposed element has been passed successful and a classifier has been developed and implemented to determine the type of wheat disease. The newest work is that computer diagnostics allows to detect the symptoms of plants disease when photographing leaves by means of GLCM matrices and interpreting the results using fuzzy logic. The proposed approach when grouped by 25 images allows to obtain reliable recognition in more than 90% of cases. In the future, the developed software has all the chances of being introduced into autonomous UAVs for automatic recognition of areas damaged by pathologies, sown with various cultivated plants. Successful integration of the developed software into agriculture will reduce the physical burden of farmers, will allow time to diagnose emerging foci of diseases of cultivated plants, after the elimination of which the yield will increase.

Computerized texture analysis characterizes spatial patterns of image intensity, which originate in the structure of tissues. However, a number of texture descriptors also depend on local average image intensity and/or contrast. This variations, known as image nonuniformity (inhomogeneity) artefacts often occur, e.g. in MRI. Their presence may lead to errors in tissue description. This unwanted effect is explained in this paper using statistical texture descriptors applied for MRI slices of a normal and fibrotic liver. To reduce the errors, correction of image spatial nonuniformity prior to texture analysis is performed. The issue of sensitivity of popular texture parameters to image nonuniformities is discussed. It is illustrated by classification examples of natural Brodatz textures, digitally modified to account for inhomogeneities – modeled as smooth variations of image intensity and contrast. A set of texture features is identified which represent certain immunity to image inhomogeneities.

In this paper we present a robust-encoded watermarking method applied to color images for copyright protection, which presents robustness against several geometric and signal processing distortions. Trade-off between payload, robustness and imperceptibility is a very important aspect which has to be considered when a watermark algorithm is designed. In our proposed scheme, previously to be embedded into the image, the watermark signal is encoded using a convolutional encoder, which can perform forward error correction achieving better robustness performance. Then, the embedding process is carried out through the discrete cosine transform domain (DCT) of an image using the image normalization technique to accomplish robustness against geometric and signal processing distortions. The embedded watermark coded bits are extracted and decoded using the Viterbi algorithm. In order to determine the presence or absence of the watermark into the image we compute the bit error rate (BER) between the recovered and the original watermark data sequence. The quality of the watermarked image is measured using the well-known indices: Peak Signal to Noise Ratio (PSNR), Visual Information Fidelity (VIF) and Structural Similarity Index (SSIM). The color difference between the watermarked and original images is obtained by using the Normalized Color Difference (NCD) measure. The experimental results show that the proposed method provides good performance in terms of imperceptibility and robustness. The comparison among the proposed and previously reported methods based on different techniques is also provided.

O monitoramento do meio ambiente e suas mudanças requer a análise de uma grade quantidade de imagens muitas vezes coletadas por satélites. No entanto, variações nos sinais devido a mudanças nas condições atmosféricas frequentemente resultam num deslocamento da distribuição dos dados para diferentes locais e datas. Isso torna difícil a distinção dentre as várias classes de uma base de dados construída a partir de várias imagens. Neste trabalho introduzimos uma nova abordagem de classificação supervisionada, chamada Classifica-Normaliza-Classifica (CNC), para amenizar o problema de deslocamento dos dados. A proposta é implementada usando dois classificadores. O primeiro é treinado em imagens não normalizadas de refletância de topo de atmosfera para distinguir dentre pixels de uma classe de interesse (CDI) e pixels de outras categorias (e.g. floresta versus não-floresta). Dada uma nova imagem de teste, o primeiro classificador gera uma segmentação das regiões da CDI e então um vetor mediano é calculado para os valores espectrais dessas áreas. Então, esse vetor é subtraído de cada pixel da imagem e portanto fixa a distribuição de dados de diferentes imagens num mesmo referencial. Finalmente, o segundo classificador, que é treinado para minimizar o erro de classificação em imagens já centralizadas pela mediana, é aplicado na imagem de teste normalizada no segundo passo para produzir a segmentação binária final. A metodologia proposta foi testada para detectar desflorestamento em pares de imagens co-registradas da Landsat 8 OLI sobre a floresta Amazônica. Experimentos usando imagens multiespectrais de refletância de topo de atmosfera mostraram que a CNC obteve maior acurácia na detecção de desflorestamento do que classificadores aplicados em imagens de refletância de superfície fornecidas pelo United States Geological Survey. As acurácias do método proposto também se mostraram superiores às obtidas pelas máscaras de desflorestamento do programa PRODES. Monitoring natural environments and their changes over time requires the analysis of a large amount of image data, often collected by orbital remote sensing platforms. However, variations in the observed signals due to changing atmospheric conditions often result in a data distribution shift for different dates and locations making it difficult to discriminate between various classes in a dataset built from several images. This work introduces a novel supervised classification framework, called Classify-Normalize-Classify (CNC), to alleviate this data shift issue. The proposed scheme uses a two classifier approach. The first classifier is trained on non-normalized top-of-the-atmosphere reflectance samples to discriminate between pixels belonging to a class of interest (COI) and pixels from other categories (e.g. forest vs. non-forest). At test time, the estimated COI’s multivariate median signal, derived from the first classifier segmentation, is subtracted from the image and thus anchoring the data distribution from different images to the same reference. Then, a second classifier, pre-trained to minimize the classification error on COI median centered samples, is applied to the median-normalized test image to produce the final binary segmentation. The proposed methodology was tested to detect deforestation using bitemporal Landsat 8 OLI images over the Amazon rainforest. Experiments using top-of-the-atmosphere multispectral reflectance images showed that the deforestation was mapped by the CNC framework more accurately as compared to running a single classifier on surface reflectance images provided by the United States Geological Survey (USGS). Accuracies from the proposed framework also compared favorably with the benchmark masks of the PRODES program.

This study uses 2010–2011 Landsat Thematic Mapper (TM) imagery to estimate total forested area in Haiti. The thematic map was generated using radiometric normalization of digital numbers by a modified normalization method utilizing pseudo-invariant polygons (PIPs), followed by supervised classification of the mosaicked image using the Food and Agriculture Organization (FAO) of the United Nations Land Cover Classification System. Classification results were compared to other sources of land-cover data produced for similar years, with an emphasis on the statistics presented by the FAO. Three global land cover datasets (GLC2000, Globcover, 2009 , and MODIS MCD12Q1), and a national-scale dataset (a land cover analysis by Haitian National Centre for Geospatial Information (CNIGS)) were reclassified and compared. According to our classification, approximately 32.3% of Haiti's total land area was tree covered in 2010–2011. This result was confirmed using an error-adjusted area estimator, which predicted a tree covered area of 32.4%. Standardization to the FAO's forest cover class definition reduces the amount of tree cover of our supervised classification to 29.4%. This result was greater than the reported FAO value of 4% and the value for the recoded GLC2000 dataset of 7.0%, but is comparable to values for three other recoded datasets: MCD12Q1 (21.1%), Globcover (2009) (26.9%), and CNIGS (19.5%). We propose that at coarse resolutions, the segmented and patchy nature of Haiti's forests resulted in a systematic underestimation of the extent of forest cover. It appears the best explanation for the significant difference between our results, FAO statistics, and compared datasets is the accuracy of the data sources and the resolution of the imagery used for land cover analyses. Analysis of recoded global datasets and results from this study suggest a strong linear relationship (R2 = 0.996 for tree cover) between spatial resolution and land cover estimates.

This paper discuss an intelligent space concepts, goals and developments. The review presents an analysis of seven intelligent meeting rooms, equipment and developed services. One of the main goals of intelligent space is the development of proactive services. Realization of such types of services requires the analysis of current situation in a room as well as behaviour of the audience. Implementation of methods for facial features analysis are the first step for this goal destination. This paper presents an algorithm for facial image normalization and recognition as well as a developed system for automatic registration and identification of meeting participants in the intelligent room. The developed algorithm is intended for processing of low resolution facial images with approximate size of 30x30 pixels. The experiments shows distribution of participants recognition rate by variety of their face sizes. In addition, implementation of blur estimation method at preliminary stage of facial image processing shows an increase of the whole system speed as well as a decrease in face recognition error rate.

This paper introduce the use of image normalization algorithm and SVD decomposition to generate a hash value of a digital image. SVD decomposition is an important linear algebra tool, which is often used in pattern recognition, digital watermarking and other signal processing fields, on the other hand image normalization is an algorithm that has been shown to be robust to different kinds of geometric attacks such like rotation, scaling and flipping. using the image normalization algorithm as a preprocessing step we can increase the robustnes of the hash value.

The present paper deals with an application of the image normalization technique for certain classes of Wiener–Hopf operators (WHOs) associated to ill-posed boundary-transmission value problems. We briefly describe the method of normalization and then apply it to boundary-transmission value problems issued from diffraction problems for a junction of two half-planes, which are relevant in mathematical physics applications. For each boundary-transmission value problem, we analyze the conditions under which the associated operator and the equivalent WHO are not normally solvable, and define the corresponding image normalized operators.

O objetivo deste trabalho foi estudar as mudanças no comportamento espectral da cultura da soja, por meio dos perfis espectrais temporais dos índices de vegetação NDVI e GVI, expressos em diferentes valores físicos: fator de reflectância bidirecional (FRB) aparente, de superfície e normalizado derivados de imagens Landsat 5/TM. Foi monitorada área de cultura de soja localizada próxima ao município de Cascavel - PR, utilizando cinco imagens da safra de 2004/2005, sendo realizados nessas imagens os procedimentos de transformação radiométrica, correção atmosférica e normalização, determinando valores físicos dos fatores de reflectância bidirecional aparente, de superfície e normalizado, respectivamente. Com o intuito de caracterizar a resposta espectral da biomassa da soja, geraram-se imagens referentes aos índices de vegetação NDVI e GVI. Como resultado, a cultura mostrou-se diferente para os tratamentos dos fatores de reflectância bidirecional aparente, de superfície e de normalização. Por meio dos perfis médios espectrais do NDVI e GVI, foi possível acompanhar todo o ciclo da cultura da soja, caracterizando o seu desenvolvimento. Observou-se, ainda, que os dados provenientes do fator de reflectância bidirecional normalizado descaracterizaram a curva espectral da cultura da soja, principalmente em meio à fase de crescimento vegetativo, na data de 9-12-2004.The objective of this study was to analyze changes in the spectral behavior of the soybean crop through spectral profiles of the vegetation indexes NDVI and GVI, expressed by different physical values such as apparent bi-directional reflectance factor (BRF), surface BRF, and normalized BRF derived from images of the Landsat 5/TM. A soybean area located in Cascavel, Paraná, was monitored by using five images of Landsat 5/TM during the 2004/2005 harvesting season. The images were submitted to radiometric transformation, atmospheric correction and normalization, determining physical values of apparent BRF, surface BRF and normalized BRF. NDVI and GVI images were generated in order to distinguish the soybean biomass spectral response. The treatments showed different results for apparent, surface and normalized BRF. Through the profiles of average NDVI and GVI, it was possible to monitor the entire soybean cycle, characterizing its development. It was also observed that the data from normalized BRF negatively affected the spectral curve of soybean crop, mainly, during the phase of vegetative growth, in the 12-9-2004 image.

Color image segmentation is a very emerging topic in current image processing research. An optimal technique for the same is always sought by the researchers of this field. In this paper, an efficient approach for color image segmentation is proposed. Here, the input color image is first converted from RGB to HSV color space. The V channel of the HSV converted image is extracted and normalized between 0 and 1. Then this normalized V channel is sent as input to Fuzzy C Means (FCM) algorithm. The fuzzy segmented image is then thresholded with Otsu’s method. The thresholded image is then filtered by sobel filter and sent as input to the Meyer’s watershed algorithm. This produces the final segmented image of the original color image. The proposed approach is found very efficient after analyzing and comparing the results with previously existed watershed algorithm in terms of the MSE and PSNR values.

Part 6: Pattern Recognition and Image Processing; International audience; In this paper we present a new approach to registration and sequencing of microscope images obtained from serial sections of large blood vessels at macroscopic levels of magnification. It is assumed that subsequent section images may be located inadequately in the image series. Translations and rotations of the object of interest can occur. Some images can be also reflected vertically or horizontally. The proposed algorithm is based on the center of gravity estimation and the phase-only correlation (POC) and uses standard image normalization as a preprocessing procedure. The method is fully-automatic and robust to common image distortions. The quality of registration is measured by the mean value of the sum of absolute difference between images. This criterion can be used also for slide images sequencing, when the image acquisition is performed independently for each section. A set of experiments, carried out using sampled microscopic images of a vein section, proves experimentally the effectiveness of the proposed approach.

The thickness of the intima-media complex (IMC) of the common carotid artery (CCA) wall is important in the evaluation of the risk for the development of atherosclerosis. This paper presents a fully automated algorithm for the segmentation of the IMC. The segmentation of the IMC of the CCA wall is important for the evaluation of the intima media thickness (IMT) on B-mode ultrasound images. The presented algorithm is based on active contours and active contours without edges. It begins with image normalization, followed by speckle removal. The level set formulation of Chan and Vese using random initialization provides a segmentation of the CCA ultrasound (US) images into different distinct regions, one of which corresponds to the carotid wall region above the lumen whilst another corresponds to the carotid wall region below the lumen and includes the IMC. The results of the corresponding segmentation combined with anatomical information provide a very accurate outline of the lumen-intima boundary. This outline serves as an excellent initialization for segmentation of the IMC using parametric active contours. The method lends itself to the development of a fully automated method for the delineation of the IMC. The mean and standard deviation of the thickness of the automatically segmented regions are 0.65 mm /0.17 mm and the corresponding values for the ground truth IMT are 0.66 mm /0.18 mm. The Wilcoxon rank sum test shows no significant difference. © 2011 IEEE. 8053 8057 Conference code: 87843 Cited By :12

This paper proposes the use of hybrid Hidden Markov Model (HMM)/Artificial Neural Network (ANN) models for recognizing unconstrained offline handwritten texts. The structural part of the optical models has been modeled with Markov chains, and a Multilayer Perceptron is used to estimate the emission probabilities. This paper also presents new techniques to remove slope and slant from handwritten text and to normalize the size of text images with supervised learning methods. Slope correction and size normalization are achieved by classifying local extrema of text contours with Multilayer Perceptrons. Slant is also removed in a nonuniform way by using Artificial Neural Networks. Experiments have been conducted on offline handwritten text lines from the IAM database, and the recognition rates achieved, in comparison to the ones reported in the literature, are among the best for the same task. © 2006 IEEE., The authors acknowledge the valuable help provided by Moises Pastor, Juan Miguel Vilar, Alex Graves, and Marcus Liwicki. Thanks are also due to the reviewers and the Editor-in-Chief for their many valuable comments and suggestions. This work has been partially supported by the Spanish Ministerio de Educacion y Ciencia (TIN2006-12767) and by the BPFI 06/250 Scholarship from the Conselleria d'Empresa, Universitat i Ciencia, Generalitat Valenciana.

En este artículo se presenta una técnica de marca de agua robusta a distorsiones geométricas y otros esquemas de procesamiento de señales. En el método de marca de agua propuesto, se hace uso de una técnica de normalización de imágenes para obtener características invariantes de la imagen ante las distorsiones geométricas. Los procesos de inserción y detección de la marca de agua se realizan en el dominio de la Transformada Discreta del Coseno (DCT). Una clasificación de texturas basada en el domino de la DCT se usa para clasificar cada bloque de la imagen a fin de poder insertar una marca de agua fuerte, manteniendo al mismo tiempo la imperceptibilidad de la misma. La técnica propuesta es una técnica de marca de agua pública, en la cual, la imagen original no está disponible en el proceso de detección de la marca de agua. Los resultados experimentales muestran la imperceptibilidad de la marca de agua y su robustez ante las distorsiones geométricas, como son rotación, escalamiento, transformaciones Affine, y otros esquemas de procesamiento de señales, tales como compresión JPEG, contaminación de imagen por ruido Gaussiano e impulsivo. This paper presents a robust watermarking method against geometric distortions and several other signal processing schemes. In the proposed watermarking method, image normalization is used to get geometric invariant features. The watermark embedding and detection process are carried out in the Discrete Cosine Transform (DCT) domain. A DCT based texture classification is used to classify each image block to embed a stronger as possible watermark, while maintaining watermark imperceptibility. The proposed watermarking scheme is a public watermarking, where the original image is not available for watermark detection. The experimental results show the watermark imperceptibility and robustness against geometric distortion such as rotation, scaling and various other Affine transformation, and common signal processing schemes, such as JPEG compression, Gaussian and impulsive noise contamination.

Digital watermarking is one of the techniques for copyright protection. In this paper, a normalization-based robust image watermarking scheme which encompasses singular value decomposition (SVD) and discrete cosine transform (DCT) techniques is proposed. For the proposed scheme, the host image is first normalized to a standard form and divided into non-overlapping image blocks. SVD is applied to each block. By concatenating the first singular values (SV) of adjacent blocks of the normalized image, a SV block is obtained. DCT is then carried out on the SV blocks to produce SVD-DCT blocks. A watermark bit is embedded in the highfrequency band of a SVD-DCT block by imposing a particular relationship between two pseudo-randomly selected DCT coefficients. An adaptive frequency mask is used to adjust local watermark embedding strength. Watermark extraction involves mainly the inverse process. The watermark extracting method is blind and efficient. Experimental results show that the quality degradation of watermarked image caused by the embedded watermark is visually transparent. Results also show that the proposed scheme is robust against various image processing operations and geometric attacks., {"references":["S.W. Foo, H.S. Muh, and N.M. Mei \"Image watermarking using timefrequency\ncompression expansion\" IEEE International Symposium on\nCircuits and Systems, 2004, pp. 201-204.","S.W. Foo, X. Feng, and M. Li \"A blind imagewatermarking scheme\nusing peak point extraction\", IEEE International Symposium on Circuits\nand Systems, 2005, pp. 4409-4412.","M. Acevedo, \"Image watermarking: properties, techniques and\nevaluation. Multimedia security: Steganography and Digital\nWatermarking Techniques for Protection of Intellectual Property, Idea\nGroup Publishing. Pennsylvania, 2005.","S.W. Foo, Y.T. Hee, and H.D. Yan, \"An adaptive image watermarking\nsystem\", IEEE Tencon 2005, pp. 509-513.","N. Cvejic and T. Seppänen, \"Audio watermarking: requirement,\nalgorithms, and benchmarking\". Digital watermarking for digital media,\nInformation Science Publishing, Pennsylvania, 2005.","J. Foote, J. Adco, and A. Girgensohn, \"Time base modulation: a new\napproach to watermarking audio\" [Electronic Version], Palo Alto\nLaboratory. California. 2003.","M.A. Suhail, \"Digital watermarking for protection of intellectual\nproperty\". Multimedia security: steganography and digital\nwatermarking techniques for protection of intellectual property, Idea\nGroup Publishing. Pennsylvania, 2006.","P. Bassia, W.T. Pitas, \"Robust Audio Watermarking In Time Domain\",\nEUSIPCO 1998, 8-11 Sept., Patras, Greece, pp. 25-28.","D. Gruhl, A. Lu, and W. Bender, \"Echo Hiding for Watermarking\", in\nProc. Information Hiding Workshop, University of Cambridge, U.K.,\n1999, pp. 295-315.\n[10] K. Seits, and T. Jahnke, \"Digital watermarking: an introduction\". In\nSeits, J, Digital watermarking for digital media, Information Science\nPublishing. Pennsylvania, 2006.\n[11] R. Garcia, \"Digital Watermarking of Audio Signals Using a\nPsychoacoustic Auditory Model and Spread Spectrum Theory\", 107th\nConvention, Audio Engineering Society, New York, 1999.\n[12] H.J. Kim, Y.H. Choi & J.W. Seok and K.H. Hong. \"Audio\nWatermarking Techniques: Intelligent Watermarking Techniques\".\nChapter 8, 185-218, 2005.\n[13] J, Seitz, S.H. Michale, \"Digital Watermarking for Digital Media,\"\nInformation Science Publishing, 2005.\n[14] N. Cvejic and T. Seppänen, \"Increasing robustness of LSB audio\nsteganography by reduced distortion LSB coding,\" Journal of\nUniversity Computer Science, vol 11, p56, 2006.\n[15] C. Hsieh. & P. Tsou. \"Blind Cepstrum Domain Audio Watermarking\nBased on Time Energy Features\". 4th Int. Conf. on Digital Signal\nProcessing, 705-708, 2004.\n[16] K.N. Garcia. \"Digital Watermarking of Audio Signals Using a\nPsychoacoustic Auditory Model and Spread Spectrum Theory\". 107th\nConvention, Audio Engineering Society, preprint 5073, 2006.\n[17] L. Wu, P.C. Su and M. Kuo \"Robust Audio Watermarking for Copyright\nProtection\". SPIE-s 44th Annual Meeting Advanced Signal Processing\nAlgorithms, Architectures, and Implementations IX. 2003.\n[18] B. Vladimir, K.E. Rao. \"An Efficient Implementation of the Forward\nand Inverse MDCT in MPEG Audio Coding\". IEEE Signal Processing\nLetters, Vol.8, No.2, 2005."]}

This work explores the segmentation of the intima-media complex (IMC) of the common carotid artery (CCA) wall for the evaluation of the intima media thickness (IMT) on B-mode ultrasound images. The IMT provides important clinical information for the evaluation of the risk of developing atherosclerosis. The algorithm begins with speckle removal, which is followed by the use of a Hough transform for boundary detection and image normalization. The corresponding results provide the initial statistical information needed for a Markov random field (MRF) segmentation. The method lends itself to the development of a fully automatic method for the delineation of the IMC. The mean and standard deviation of the automatically segmented results are 0.7855 and 0.1738mm and the corresponding value for the ground truth IMT are 0.7959 and 0.1875mm. The Wilcoxon rank sum test shows no significant differences. Future work will investigate the proposed method using a larger number of tissue classes and on more subjects. © 2010 IEEE. Sponsors: University of Ioannina National Technical University of Athens University of Patras Ionian University Unit Med. Technol. Intelligent Inf. Syst., Univ. Ioannina Conference code: 83786 Cited By :3

Digital watermarking has become an important technique for copyright protection but its robustness against attacks remains a major problem. In this paper, we propose a normalizationbased robust image watermarking scheme. In the proposed scheme, original host image is first normalized to a standard form. Zernike transform is then applied to the normalized image to calculate Zernike moments. Dither modulation is adopted to quantize the magnitudes of Zernike moments according to the watermark bit stream. The watermark extracting method is a blind method. Security analysis and false alarm analysis are then performed. The quality degradation of watermarked image caused by the embedded watermark is visually transparent. Experimental results show that the proposed scheme has very high robustness against various image processing operations and geometric attacks., {"references":["J. J. K. O'Ruanaidh, W.J. Downling, and F.M. Boland, \"Watermarking \ndigital images for copyright protection,\" in Proc. Inst. Elect. Eng., vol.\n143, no. 4, pp. 250-256, Aug. 1996.","I. J. Cox, J. Kilian, F. T. Leighton, and T. Shamoon,\"Secure spread\nspectrum watermarking for multimedia,\" IEEE Trans. Image Process.,\nvol. 6, no. 12, pp. 1673-1687, Dec. 1997.","Ning Bi, Qiyu Sun, Daren Huang, Zhihua Yang, Jiwu Huang,\"Robust\nImage Watermarking Based on Multiband Wavelets and Empirical\nMode Decomposition,\" IEEE Transactions on Image Processing,\nVolume 16, Issue 8, Aug. 2007 Page(s):1956 - 1966","Ching-Yung Lin and Shih-Fu Chang, A Robust Image Authentication\nMethod Distinguishing JPEG Compression from Malicious\nManipulation, IEEE Transactions on Circuits and Systems for Video\nTechnology, Vol. 11 No. 2, 2001, pp. 129-138","P.S.L.M. Barreto, H.Y. Kim, andV. Rijmen,\"Toward secure public-\nkey blockwise fragile authentication watermarking,\" in Proc. Inst. Elect.\nEng., vol. 149, no. 2, pp. 57-62, Apr. 2002.","N. Singhal, Y.Y. Lee, and S.U. Lee, \"Robust image watermarking\nusing local Zernike moments,\" Science Direct. Image Process. vol. 11,\nno. 6, pp. 585-595, Jun. 2008.","Xiang-yang Wang, Li-min Hou and Jun Hu \"A feature-based robust\ndigital image watermarking scheme,\" IEEE Transactions on Image\nProcessing, Volume 15, Issue 10, Oct. 2007 Page(s):3189 - 3200.","Ching-Yung Lin and Shi-Fu Chang,\"Semi-fragile watermarking for\nauthenticating JPEG visual content\", SPIE, Security and Watermarking\nof Multimedia Contents, pp.140-151, 2000.","Zhe-Ming Lu, Chun-He Liu, Dian-Guo Xu, Sheng-He Sun,\" Semi-\nfragile image watermarking method based on index constrained vector\nquantization,\" Electronics Letters, Volume 39, Issue 1, 9 Jan 2003\nPage(s):35 - 36.\n[10]C.S. Lu and H.Y.M. Liao,\"Multipurpose watermarking for image\nauthentication and protection,\" IEEE Trans. Image Process., vol. 10, pp.\n1579-1592, Oct. 2001.\n[11] Fan Gu, Zhe-Ming Lu, Jeng-Shyang Pan,\"Invariant Watermarking\nUsing Zernike Moments,\" IEEE International Symposium on Circuits\nand Systems, 2005. Vol. 5, Page(s):4417 - 4420.\n[12] Zhe-Ming Lu, Dian-Guo Xu, Sheng-He Sun, \"A Novel Watermarking\nScheme based on SVD and Zernike Moments,\" IEEE Transactions on\nImage Processing, Volume 14, Issue 6, June 2005 Page(s):822 - 831\n[13] Z. M. Lu and S. H. Sun, \"Digital image watermarking technique based\non vector quantization,\" Electron. Lett., vol. 36, no. 4, pp. 303-305, Feb.\n2000.\n[14] Z. M. Lu, J. S. Pan, and S. H. Sun, \"VQ-based digital image\nwatermarking method,\" Electron. Lett., vol. 36, no. 14, pp. 1201-1202,\nJul. 2000.\n[15] Z. M. Lu, C. H. Liu, and S. H. Sun, \"Digital image watermarking\ntechnique based on block truncation coding with vector quantization,\"\nChinese J. Electron., vol. 11, no. 2, pp. 152-157, Apr. 2002.\n[16] E.-H. Yang and G. Wu, \"Joint compression and blind watermarking: A\ncase study in the JPEG-compatible scenario,\" Proc. of the 43th Allerton\nConference on Communications, Control, and Computing, September\n28-30, 2005.\n[17] Wong, P.H.W. and Au, O.C., \"A blind watermarking technique in JPEG\ncompressed domain using image normalization,\" Proceedings of\nInternational Conference on Image Processing. Vol. 3, Issue 24-28, pp.\n497 - 500, June 2002.\n[18] R. Liu and T. Tan, \"A new normalization-based image watermarking\nmethod,\" In Proc. of the 4th Asian Conference on Computer Vision,\nvolume I, pages 63--67, January 2000.\n[19] V. Gorodetski, L.Popyack, V. Samoilov, and V.Skormi, \"SVD-based\nApproach to Transparent Embedding Data into Digital Images,\" in Proc.\nInt. Workshop, MMM-ACNS, St. Petersburg, Russia, 2001, pp. 263-274.\n[20] K.L. Chung, C.H. Shen, L.C. Chang, \"A nocel SVD- and VQ-based\nimage hiding scheme\" Pattern Recognition Letter, pp 1051-1058, 2001.\n[21] D.V.S. Chandra, \"Digital image watermarking using singular value\ndecomposition,\" in Proc. of 45th IEEE Midwest Symposium on Circuits\nand System, Tulsa, OK, 2002, pp. 264-267.\n[22] R. Liu and T. Tan, \"An SVD-Based Watermarking Scheme for\nProtecting Rightful Ownership,\" IEEE Transactions on Multimedia, vol.\n4, no. 1, pp. 121-128, March 2006.\n[23] S. Xiang, Wu, J. Huang, D. Huang, and Y. Q. Shi. Efficiently Self-\nsynchronized audio watermarking for assured audio data transmission.\nIEEE Trans. Broadcasting, 51(1):69-76, March 2005.\n[24] B. Ko, R. Nishimura, and Y. Suzuki. Time-spread echo method for\ndigital audio watermarking using PN sequences ICASSP, 2:2001-2004,\n2002.\n[25] C. C. Chang, C. C. Lin and Y. S. Hu, \"An SVD oriented watermark\nembedding scheme with high qualities for the resorted images,\"\nInternational Journal of Innovative Computing, Information and\nControl, vol.3, no.3, pp.609-620, 2007.\n[26] Xiao-Ping Zhang; Kan Li, \"Comments on \"An SVD-Based\nWatermarking Scheme for Protecting Rightful Ownership\",\" IEEE\nTransactions on Multimedia, Volume 7, Issue 3, June 2005 Page(s):593\n- 594.\n[27] A. Shnayderman, A. Gusev, and A. M. Eskicioglu, \"An SVD-based\nGrayscale Image Quality Measure for Local and Global Assessment,\"\nIEEE Transactions on Image Processing, vol. 15, no. 2, pp. 422-429,\nFeb 2006.\n[28] A. S. Lewis and G. Knowles, \"Image Compression Using the 2-D\nWavelet Transform,\" IEEE Transactions on Image Processing, vol. 1,\nno. 2, pp. 244-250, Apr 1992."]}

O objetivo deste trabalho foi estudar as mudanças no comportamento espectral da cultura da soja, por meio dos perfis espectrais temporais dos índices de vegetação NDVI e GVI, expressos em diferentes valores físicos: fator de reflectância bidirecional (FRB) aparente, de superfície e normalizado derivados de imagens Landsat 5/TM. Foi monitorada área de cultura de soja localizada próxima ao município de Cascavel - PR, utilizando cinco imagens da safra de 2004/2005, sendo realizados nessas imagens os procedimentos de transformação radiométrica, correção atmosférica e normalização, determinando valores físicos dos fatores de reflectância bidirecional aparente, de superfície e normalizado, respectivamente. Com o intuito de caracterizar a resposta espectral da biomassa da soja, geraram-se imagens referentes aos índices de vegetação NDVI e GVI. Como resultado, a cultura mostrou-se diferente para os tratamentos dos fatores de reflectância bidirecional aparente, de superfície e de normalização. Por meio dos perfis médios espectrais do NDVI e GVI, foi possível acompanhar todo o ciclo da cultura da soja, caracterizando o seu desenvolvimento. Observou-se, ainda, que os dados provenientes do fator de reflectância bidirecional normalizado descaracterizaram a curva espectral da cultura da soja, principalmente em meio à fase de crescimento vegetativo, na data de 9-12-2004. The objective of this study was to analyze changes in the spectral behavior of the soybean crop through spectral profiles of the vegetation indexes NDVI and GVI, expressed by different physical values such as apparent bi-directional reflectance factor (BRF), surface BRF, and normalized BRF derived from images of the Landsat 5/TM. A soybean area located in Cascavel, Paraná, was monitored by using five images of Landsat 5/TM during the 2004/2005 harvesting season. The images were submitted to radiometric transformation, atmospheric correction and normalization, determining physical values of apparent BRF, surface BRF and normalized BRF. NDVI and GVI images were generated in order to distinguish the soybean biomass spectral response. The treatments showed different results for apparent, surface and normalized BRF. Through the profiles of average NDVI and GVI, it was possible to monitor the entire soybean cycle, characterizing its development. It was also observed that the data from normalized BRF negatively affected the spectral curve of soybean crop, mainly, during the phase of vegetative growth, in the 12-9-2004 image.

Neural processors have shown good results for detecting a certain character in a given input matrix. In this paper, a new idead to speed up the operation of neural processors for character detection is presented. Such processors are designed based on cross correlation in the frequency domain between the input matrix and the weights of neural networks. This approach is developed to reduce the computation steps required by these faster neural networks for the searching process. The principle of divide and conquer strategy is applied through image decomposition. Each image is divided into small in size sub-images and then each one is tested separately by using a single faster neural processor. Furthermore, faster character detection is obtained by using parallel processing techniques to test the resulting sub-images at the same time using the same number of faster neural networks. In contrast to using only faster neural processors, the speed up ratio is increased with the size of the input image when using faster neural processors and image decomposition. Moreover, the problem of local subimage normalization in the frequency domain is solved. The effect of image normalization on the speed up ratio of character detection is discussed. Simulation results show that local subimage normalization through weight normalization is faster than subimage normalization in the spatial domain. The overall speed up ratio of the detection process is increased as the normalization of weights is done off line., {"references":["R. Klette, and Zamperon, Handbook of image processing operators, John\nWiley & Sonsltd, 1996.","H. A. Rowley, S. Baluja, and T. Kanade, \" Neural Network - Based Face\nDetection,\" IEEE Trans. on Pattern Analysis and Machine Intelligence,\nVol. 20, No. 1, pp. 23-38, 1998.","H. Schneiderman and T. Kanade, \"Probabilistic modeling of local\nappearance and spatial relationships for object recognition, \" In IEEE\nConference on Computer Vision and Pattern Recognition (CVPR), pp.\n45-51, SantaBarbara, CA, 1998.","R. Feraud, O. Bernier, J. E. Viallet, and M. Collobert, \"A Fast and\nAccurate Face Detector for Indexation of Face Images,\" Proceedings of\nthe Fourth IEEE International Conference on Automatic Face and\nGesture Recognition, Grenoble, France, 28-30 March, 2000.","Y. Zhu, S. Schwartz, and M. Orchard, \"Fast Face Detection Using\nSubspace Discriminate Wavelet Features,\" Proc. of IEEE Computer\nSociety International Conference on Computer Vision and Pattern\nRecognition (CVPR'00), South Carolina, June 13 - 15, 2000, Vol.1, pp.\n1636-1643.","H. M. El-Bakry, \"Automatic Human Face Recognition Using Modular\nNeural Networks,\" Machine Graphics & Vision Journal (MG&V), Vol.\n10, No. 1, 2001, pp. 47-73.","S. Srisuk and W. Kurutach, \"A New Robust Face Detection in Color\nImages,\" Proc. of IEEE Computer Society International Conference on\nAutomatic Face and Gesture Recognition, Washington D.C., USA, May\n20-21, 2002, pp. 306-311.","H. M. El-Bakry, \"Face detection using fast neural networks and image\ndecomposition,\" Neurocomputing Journal, Vol. 48, 2002, pp. 1039-\n1046.","H. M. El-Bakry, \"Human Iris Detection Using Fast Cooperative Modular\nNeural Networks and Image Decomposition,\" Machine Graphics &\nVision Journal (MG&V), Vol. 11, No. 4, 2002, pp. 498-512.\n[10] Hazem M. El-Bakry, and Qiangfu Zhao, \"Fast Object/Face Detection\nUsing Neural Networks and Fast Fourier Transform,\" International\nJournal of Signal Processing, Vol.1, No.3, pp. 182-187, 2004.\n[11] Hazem M. El-Bakry, and Qiangfu Zhao, \"A Modified Cross Correlation\nin the Frequency Domain for Fast Pattern Detection Using Neural\nNetworks,\" International Journal of Signal Processing, Vol.1, No.3, pp.\n188-194, 2004.\n[12] Hazem M. El-Bakry, and Qiangfu Zhao, \"Face Detection Using Fast\nNeural Processors and Image Decomposition,\" International Journal of\nComputational Intelligence, Vol.1, No.4, pp. 313-316, 2004.\n[13] Hazem M. El-Bakry, and Qiangfu Zhao, \"Fast Complex Valued Time\nDelay Neural Networks,\" International Journal of Computational\nIntelligence, Vol.2, No.1, pp. 16-26, 2005.\n[14] Hazem M. El-Bakry, and Qiangfu Zhao, \"A Fast Neural Algorithm for\nSerial Code Detection in a Stream of Sequential Data,\" International\nJournal of Information Technology, Vol.2, No.1, pp. 71-90, 2005.\n[15] H. M. El-Bakry, and Q. Zhao, \"Speeding-up Normalized Neural\nNetworks For Face/Object Detection,\" Machine Graphics & Vision\nJournal (MG&V), Vol. 14, No.1, 2005, pp. 29-59.\n[16] H. M. El-Bakry, and Q. Zhao, \"Fast Pattern Detection using Normalized\nNeural Networks and Cross Correlation in the Frequency Domain,\"\nEURASIP Journal on Applied Signal Processing,. Special Issue on\nAdvances in Intelligent Vision Systems: Methods and ApplicationsÔÇö\nPart I, Vol. 2005, No. 13, 1 August 2005, pp. 2054-2060.\n[17] S. Ben-Yacoub, B. Fasel, and J. Luettin, \"Fast Face Detection using MLP\nand FFT,\" Proc. of the Second International Conference on Audio and\nVideo-based Biometric Person Authentication (AVBPA'99), 1999.\n[18] B. Fasel, \"Fast Multi-Scale Face Detection,\" IDIAP-Com 98-04, 1998.\n[19] S. Ben-Yacoub, \"Fast Object Detection using MLP and FFT,\" IDIAP-RR\n11, IDIAP, 1997.\n[20] James W. Cooley and John W. Tukey, \"An algorithm for the machine\ncalculation of complex Fourier series,\" Math. Comput. 19, 297-301\n(1965).\n[21] J. P. Lewis, \"Fast Normalized Cross Csorrelation\", Available\nfrom:\n[22] H. M. El-Bakry, \"Comments on Using MLP and FFT for Fast\nObject/Face Detection,\" Proc. of IEEE IJCNN-03, Portland, Oregon, pp.\n1284-1288, July, 20-24, 2003.\n[23] H. M. El-Bakry, and H. Stoyan, \"Fast Neural Networks for Object/Face\nDetection,\" Proc. of the 30th Anniversary SOFSEM Conference on\nCurrent Trends in Theory and Practice of Computer Science, 24-30\nJanuary, 2004, Hotel VZ MERIN, Czech Republic.\n[24] H. M. El-Bakry, and H. Stoyan, \"Fast Neural Networks for Sub-Matrix\n(Object/Face) Detection,\" Proc. of IEEE International Symposium on\nCircuits and Systems, Vancouver, Canada, 23-26 May, 2004.\n[25] H. M. El-Bakry, \"Fast Sub-Image Detection Using Neural Networks and\nCross Correlation in Frequency Domain,\" Proc. of IS 2004: 14th Annual\nCanadian Conference on Intelligent Systems, Ottawa, Ontario, 6-8 June,\n2004.\n[26] H. M. El-Bakry, and H. Stoyan, \"Fast Neural Networks for Code\nDetection in a Stream of Sequential Data,\" Proc. of CIC 2004\nInternational Conference on Communications in Computing, Las Vegas,\nNevada, USA, 21-24 June, 2004.\n[27] H. M. El-Bakry, \"Fast Neural Networks for Object/Face Detection,\"\nProc. of 5th International Symposium on Soft Computing for Industry\nwith Applications of Financial Engineering, June 28 - July 4, 2004,\nSevilla, Andalucia, Spain.\n[28] H. M. El-Bakry, and H. Stoyan, \"A Fast Searching Algorithm for Sub-\nImage (Object/Face) Detection Using Neural Networks,\" Proc. of the 8th\nWorld Multi-Conference on Systemics, Cybernetics and Informatics, 18-\n21 July, 2004, Orlando, USA.\n[29] H. M. El-Bakry, and H. Stoyan, \"Fast Neural Networks for Code\nDetection in Sequential Data Using Neural Networks for\nCommunication Applications,\" Proc. of the First International\nConference on Cybernetics and Information Technologies, Systems and\nApplications: CITSA 2004, 21-25 July, 2004. Orlando, Florida, USA,\nVol. IV, pp. 150-153.\n[30] H. M. El-bakry, M. A. Abo-elsoud, and M. S. Kamel, \"Fast Modular\nNeural Networks for Human Face Detection,\" Proc. of IEEE-INNSENNS\nInternational Joint Conference on Neural Networks, Como, Italy,\nVol. III, pp. 320-324, 24-27 July, 2000.\n[31] H. M. El-bakry, \"Fast Iris Detection using Cooperative Modular Neural\nNets,\" Proc. of the 6th International Conference on Soft Computing, 1-4\nOct., 2000, Japan.\n[32] H. M. El-Bakry, \"Automatic Human Face Recognition Using Modular\nNeural Networks,\" Machine Graphics & Vision Journal (MG&V), Vol.\n10, No. 1, 2001, pp. 47-73.\n[33] H. M. El-bakry, \"Fast Iris Detection Using Cooperative Modular Neural\nNetworks,\" Proc. of the 5th International Conference on Artificial Neural\nNets and Genetic Algorithms, pp. 201-204, 22-25 April, 2001, Prague,\nCzech Republic.\n[34] H. M. El-bakry, \"Fast Iris Detection Using Neural Nets,\" Proc. of the\n14th Canadian Conference on Electrical and Computer Engineering,\npp.1409-1415, 13-16 May, 2001, Canada.\n[35] H. M. El-bakry, \"Human Iris Detection Using Fast Cooperative Modular\nNeural Nets,\" Proc. of INNS-IEEE International Joint Conference on\nNeural Networks, pp. 577-582, 14-19 July, 2001, Washington, DC,\nUSA.\n[36] H. M. El-bakry, \"Human Iris Detection for Information Security Using\nFast Neural Nets,\" Proc. of the 5th World Multi-Conference on\nSystemics, Cybernetics and Informatics, 22-25 July, 2001, Orlando,\nFlorida, USA.\n[37] H. M. El-bakry, \"Human Iris Detection for Personal Identification Using\nFast Modular Neural Nets,\" Proc. of the 2001 International Conference\non Mathematics and Engineering Techniques in Medicine and\nBiological Sciences, pp. 112-118, 25-28 July, 2001, Monte Carlo Resort,\nLas Vegas, Nevada, USA.\n[38] H. M. El-bakry, \"Human Face Detection Using Fast Neural Networks\nand Image Decomposition,\" Proc. the fifth International Conference on\nKnowledge-Based Intelligent Information & Engineering Systems, 6-8\nSeptember 2001, Osaka-kyoiku University, Kashiwara City, Japan, pp.\n1330-1334.\n[39] H. M. El-Bakry, \"Fast Iris Detection for Personal Verification Using\nModular Neural Networks,\" Proc. of the International Conference on\nComputational Intelligence, 1-3 Oct., 2001, Dortmund, Germany, pp.-\n269-283.\n[40] H. M. El-bakry, \"Fast Cooperative Modular Neural Nets for Human Face\nDetection,\" Proc. of IEEE International Conference on Image\nProcessing, 7-10 Oct., 2001, Thessaloniki, Greece.\n[41] H. M. El-Bakry, \"Fast Face Detection Using Neural Networks and Image\nDecomposition,\" Proc. of the 6th International Computer Science\nConference, Active Media Technology, Dec. 18-20, 2001, Hong Kong -\nChina, pp. 205-215, 2001.\n[42] H. M. El-Bakry, \"Face Detection Using Fast Neural Networks and Image\nDecomposition,\" Proc. of INNS-IEEE International Joint Conference on\nNeural Networks, 14-19 May, 2002, Honolulu, Hawaii, USA."]}

International audience; Discrete orthogonal moments such as Tchebichef moments have been successfully used in the field of image analysis. However, the invariance property of these moments has not been studied mainly due to the complexity of the problem. Conventionally, the translation and scale invariant functions of Tchebichef moments can be obtained either by normalizing the image or by expressing them as a linear combination of the corresponding invariants of geometric moments. In this paper, we present a new approach that is directly based on Tchebichef polynomials to derive the translation and scale invariants of Tchebichef moments. Both derived invariants are unchanged under image translation and scale transformation. The performance of the proposed descriptors is evaluated using a set of binary characters. Examples of using the Tchebichef moments invariants as pattern features for pattern classification are also provided.

Permanently a special emphasis is given to image processing considering geometric distortions for remote sensing, and image tracking especially. We discuss an approach to affine transformation parameters search on the base of salient points which can be external and internal relative to shapes. To find affinity we use sets of image binary cuts and one-to-one point correspondence. This correspondence is determined by means of the affine-equivalent shape ratio invariance. We investigate two types of salient points on the base of binary morphology. First ones are vertices of convex hulls and second ones belong to skeletons. Finally, solution of overdetermined system of linear equations gives us affine transformation parameters. Results of the exterior points and skeleton normalization methods comparative analysis are discussed.

International audience; The early detection of breast cancer greatly improves prognosis. One of the earliest signs of cancer is the formation of clusters of microcalcifications. We introduce a novel method for microcalcification detection based on a biologically inspired adaptive model of contrast detection. This model is used in conjunction with image filtering based on anisotropic diffusion and curvilinear structure removal using local energy and phase congruency. An important practical issue in automatic detection methods is the selection of parameters: we show that the parameter values for our algorithm can be estimated automatically from the image. This way, the method is made robust and essentially free of parameter tuning. We report results on mammograms from two databases and show that the detection performance can be improved by first including a normalisation scheme.

In this paper we present two watermarking approaches that are robust to geometric distortions. The first approach is based on image normalization, in which both watermark embedding and extraction are carried out with respect to an image normalized to meet predefined moment criteria. We propose a new normalization procedure, which is invariant to affine transform attacks. The resulting watermarking scheme is suitable for public watermarking applications, where the original image is not available for watermark extraction. The second approach is based on a watermark resynchronization scheme aimed to alleviate the effects of random bending attacks. In this scheme, a deformable mesh is used to correct the distortion caused by the attack. The watermark is then extracted from the corrected image. In contrast to the first scheme, the latter is suitable for private watermarking applications, where the original image is needed during watermark detection. In both schemes we employ a direct-sequence code division multiple access (DS-CDMA) approach to embed a multi-bit watermark in the discrete cosine transform (DCT) domain of the image. Numerical experiments demonstrate that the proposed watermarking schemes are robust to a wide range of geometric attacks.

Neural networks have shown good results for detection of a certain pattern in a given image. In our previous work, a fast algorithm for object/face detection was presented. Such algorithm was designed based on cross-correlation in the frequency domain between the input image and the weights of neural networks. Our previous work also solved the problem of local subimage normalization in the frequency domain. In this paper, the effect of image normalization on the speedup ratio of pattern detection is presented. Simulation results show that local subimage normalization through weight normalization is faster than subimage normalization in the spatial domain. Moreover, the overall speedup ratio of the detection process is increased as the normalization of weights is done offline.