Search

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.

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

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.

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.

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.

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.

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

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.