Search

• The spectral characteristics of different types of deterioration are analyzed. • The normalized spectral index is constructed to preliminarily identify the deterioration. • The relationship between spectral reflectance and Schmidt rebound value is established. • The deterioration identification models are established based on hyperspectral image texture features. Deterioration investigation is an essential foundation for understanding the preservation status of stone cultural heritage, as well as for carrying out emergency and preventive conservation. Traditional photogrammetry method for deterioration investigation in stone cultural heritage heavily relies on personnel experience and has low automation. To accurately evaluate the degree of deterioration and quantify its scale, different algorithms are used to establish the rebound value prediction model and deterioration identification model based on the hyperspectral image. The effects of different wavelength selection methods and different classification models are compared. The results show that the rebound value inversion model constructed by CARS and PLS delivers the most accurate forecasts, with R2 being no less than 0.85. The maximum error of the model when applied in the field does not exceed 20%. Different types of deterioration can be initially identified by the normalized spectral index constructed from the 530 nm and 675 nm wavelengths. In addition, all four classification models based on hyperspectral imaging texture features can identify different types of deterioration. The LGBM model has the highest identification accuracy of 0.98. It also has good performance in field identification. This study provides a new method for deterioration investigation in stone cultural heritage. [ABSTRACT FROM AUTHOR]

Modifications of algorithms for the classification of single-layer, vertical development clouds, and multilayer clouds based on a probabilistic neural network and a neuro-fuzzy classifier are proposed. Clouds are classified into 16 types according to the meteorological standard, including the combined subtypes of stratus, altocumulus, cirrus, and cirrostratus clouds. The article uses a description of clouds based on information about the texture of their images on satellite images from MODIS and its products with data on the physical parameters of clouds. The structure of classification algorithms is described. The results of the use of statistical models of image texture and physical parameters of clouds for initializing membership functions for a neural-fuzzy classifier are presented. Systems of effective classification characteristics for different classification algorithms are formed based on the GRAD modified truncated search method. The recognition results of single-layer, vertical development clouds, and multilayer clouds based on the corresponding test samples and full-size sets of MODIS satellite data with different spatial resolution are discussed. [ABSTRACT FROM AUTHOR]

Calculation of co-occurrence probabilities is a popular method for determining texture features within remotely sensed digital imagery. Typically, the co-occurrence features are calculated by using a grey level co-occurrence matrix (GLCM) to store the co-occurring probabilities. Statistics are applied to the probabilities in the GLCM to generate the texture features. This method is computationally intensive since the matrix is usually sparse leading to many unnecessary calculations involving zero probabilities when applying the statistics. An improvement on the GLCM method is to utilize a grey level co-occurrence linked list (GLCLL) to store only the non-zero co-occurring probabilities. The GLCLL suffers since, to achieve preferred computational speeds, the list should be sorted. An improvement on the GLCLL is to utilize a grey level co-occurrence hybrid structure (GLCHS) based on an integrated hash table and linked list approach. Texture features obtained using this technique are identical to those obtained using the GLCM and GLCLL.The GLCHS method is implemented using the C language in a Unix environment. Based on a Brodatz test image, the GLCHS method is demonstrated to be a superior technique when compared across various window sizes and grey level quantizations. The GLCHS method required, on average, 33.4% (σ=3.08%) of the computational time required by the GLCLL. Significant computational gains are made using the GLCHS method. [Copyright &y& Elsevier]

In the foam nickel process, texture is the indicator of foam nickel performance. In order to recognize foam nickel surface defects accurately and provide guidance for production operations, this paper proposes a method for extracting foam nickel image textures based on multi-scale texture analysis. First, nonsubsampled contourlet (NSCT) is used to carry out foam nickel image multi-scale decomposition, and the lowfrequency and high-frequency components following decomposition are used to characterize different defect details. Then, the Haralick eigenvalue, which measures the foam nickel image texture information at each sub-band, is calculated. The KPCA and optimal DAG-SVM are adopted in order to reduce the parameter dimension and clarify defects. Tests are carried out on the foam nickel surface image samples, including crack, scratch, pollution, leakage, and indentation tests. The results indicate that the method proposed in this paper can extract different pieces of detailed texture information and can achieve a defect-identifying accuracy of up to 88.9%. [ABSTRACT FROM AUTHOR]

Splicing Image Forgery Identification controls and picture tampering with no proof being left behind has turned out to be exceptionally moderate and exceedingly utilized, because of presence of to a great degree intense altering apparatuses, for example, Adobe Photoshop. Along these lines, there has been a quick expansion of the digitally adjusted pictures on the Internet and prevailing press. The genuineness of a digital image experiences extreme dangers because of the ascent of capable digital image altering devices that effectively adjust the image substance without leaving any obvious hints of such changes. The splicing forgery should be possible by replicated a one/more area from source image and pasted into an objective picture to create a composite image called spliced image. In this manner, this sort of forgery is viewed as challenge issue difficult from tamper identification perspective. To influence the issue most exceedingly awful some to post preparing impacts, for example, blurring, JPEG compression, rotation and scaling perhaps presented in the spliced image. This study aims to perform quantification and data analysis following feature extraction using computational techniques to detect interesting textural and anatomical changes, these extracted features then can be used as a key to distinguish between different classes (Splicing Image and non-Splicing image). This paper presents a new framework to identify the spliced image by exploiting the image texture features, and to automatically identification of spliced images. To accurately identify the spliced image, the proposed solution uses different texture features to capture deferent texture related to the edge of the object and the colour features. We have combine these features to produce a good vector to describe the splice object. Two models have been proposed in this paper first combine the vectors of the three features and feed them to the ANN classifier. Second, use the majority voting of the result of three features to take the decision. This is followed by a ANN classifier; in this model we have trained the system with 30 training 20% validation 50% testing. We evaluated the effectiveness of the classification framework for identifying spliced images by compare the result with the manual label which is done by the people who have created the data sets. In this approach we have combine different features to capture different information and feed them to the neural network to identify the splicing image. The findings outcome from this study have shown an improved approach that automatically splicing image forgery identification. We have evaluated the splicing image forgery identification using the texture features. The identification accuracy in the technique used is about 98.06%., with 99.03% sensitivity and 96.07% specificity. [ABSTRACT FROM AUTHOR]

Soil is an important environment for crop growth. Quick and accurately access to soil nutrient content information is a prerequisite for scientific fertilization. In this work, hyperspectral imaging (HSI) technology was applied for the classification of soil types and the measurement of soil total nitrogen (TN) content. A total of 183 soil samples collected from Shangyu City (People's Republic of China), were scanned by a near-infrared hyperspectral imaging system with a wavelength range of 874-1734 nm. The soil samples belonged to three major soil types typical of this area, including paddy soil, red soil and seashore saline soil. The successive projections algorithm (SPA) method was utilized to select effective wavelengths from the full spectrum. Pattern texture features (energy, contrast, homogeneity and entropy) were extracted from the gray-scale images at the effective wavelengths. The support vector machines (SVM) and partial least squares regression (PLSR) methods were used to establish classification and prediction models, respectively. The results showed that by using the combined data sets of effective wavelengths and texture features for modelling an optimal correct classification rate of 91.8%. could be achieved. The soil samples were first classified, then the local models were established for soil TN according to soil types, which achieved better prediction results than the general models. The overall results indicated that hyperspectral imaging technology could be used for soil type classification and soil TN determination, and data fusion combining spectral and image texture information showed advantages for the classification of soil types. [ABSTRACT FROM AUTHOR]

Hardness is one of the important attributes in determining the quality of dried fruits. Hardness assessment is normally carried out by manual inspection. This method is time consuming, laborious, expensive and subjective. The objective of this study was to develop a computer vision system with a monochrome camera to classify dates based on hardness. Date samples were obtained from three different growing regions in Oman and graded into soft, semi-hard, and hard classes based on hardness. A total of 1800 date samples were imaged individually using a monochrome camera (600 dates / class). Histogram and texture features were extracted from the acquired monochrome images and used in the classification models. The overall classification accuracies in three class model (soft, semi-hard, and hard) were 66% and 71% for linear discriminant analysis (LDA) and artificial neural network (ANN), respectively. It was improved to 84% and 77% in LDA and ANN, respectively while using two class model (soft and hard (semi-hard and hard together)). The histogram features were more contributing in the date classification based on hardness than image texture features. Computer vision technique has great potential to develop online quality monitoring systems for dates and other dried fruits. [ABSTRACT FROM AUTHOR]

In order to conquer the difficulty of simultaneously recognizing the multiple defects of potatoes samples placed randomly, this paper proposed a non-destructive detection method which combined manifold learning dimension reduction algorithm based on hyperspectral information fusion and extreme learning machine (ELM) to simultaneously distinguish the multiple defects of potatoes. In this paper, 367 potatoes were picked which were made up of 111 sprouting potatoes, 90 green rind potatoes, 46 blackheart potatoes and 120 normal potatoes. The hyperspectral image acquisition system contained imaging spectroradiometer (SPECIM, V10E, Finland), data acquisition box, lighting system, electric moving stage and objective table. The reflection hyperspectral information of all those potatoes was acquired by using the hyperspectral image acquisition system, whose spectral wavelength ranged from 390 to 1040 nm. The hyperspectral information included the spectral information from 520 wave bands and the imaging information from 520 gray images. After the correction to hyperspectral data with the standard black and white board, hyperspectral data in the range of 450-990 nm, which had high signal-to-noise ratio (SNR), were selected as original spectrum for subsequent processing. To deal with the spectral information, the average spectrum was abstracted from the region of interests (ROI) on every potato sample by using the environment for visualizing images (ENVI). Comparing several data preprocessing methods, detrend was determined as the optimal spectral preprocessing method. Diffusion maps (DM), locally linear embedding (LLE) and hessian locally linear embedding (HLLE) were respectively utilized for the purpose of cutting down the dimension of spectrum data after the spectral preprocessing named detrend. To deal with the hyperspectral imaging information, every pseudo-color image of potatoes was morphologically processed before extracting 84 image texture characteristics based on gray level co-occurrence matrix (GLCM). By using successive projections algorithm (SPA), 10 texture features were properly selected, which consisted of homogeneity of 45° GLCM in R gray image, energy of 90° GLCM in R gray image, correlation of 90° GLCM in R gray image, contrast of 135° GLCM in R gray image, correlation of 0° GLCM in G gray image, contrast of 0° GLCM in G gray image, correlation of 90° GLCM in G gray image, homogeneity of 45° GLCM in B gray image, correlation of 90° GLCM in B gray image and contrast of 135° GLCM in B gray image. After the fusion of the spectral characteristics and image features, the 367 potato samples were divided into calibration set and test set. The calibration set had 250 potato samples including 74 sprouting potatoes, 59 green rind potatoes, 28 blackheart potatoes and 89 normal potatoes. The whole number of samples in test set was 117 which contained 37 sprouting potatoes, 31 green rind potatoes, 18 blackheart potatoes and 31 normal potatoes. Six models were respectively established based on support vector machine (SVM) and ELM, which were DM-SVM, LLE-SVM, HLLE-SVM, DM-ELM, LLE-ELM and HLLE-ELM. Comparing and analyzing the results of the 6 models and the spending time, we discovered that the DM was the best manifold learning dimension reduction algorithm to deduce the spectral information. We alsofound that the DM-ELM model was the best model because of the better recognition rate for recognizing the multiple defects of potatoes and spending less time. For the DM-ELM model, the single recognition rate of sprouting potatoes, green rind potatoes, blackheart potatoes and normal potatoes respectively reached 97.30%, 93.55%, 94.44% and 100%, and the mixed recognition rate reached 96.58%. It only cost 0.11 s to build the DM-ELM model. The results indicate that combining hyperspectral information fusion with manifold learning dimension reduction algorithm can simultaneously distinguish the multiple defects of potatoes. [ABSTRACT FROM AUTHOR]

Due to high protein, low fat, high vitamin and mineral content, beef is regarded as an important meat item which is consumed by human in regular basis. In addition, with the improvement of people's living standard, different quality parameters such as beef tenderness, water retention and other edible quality indicators have become important factors to consumers' satisfaction. Sensory evaluation and shear force measurement are primarily two methods for measurement of beef tenderness, which are now considered as traditional methods. However, with improvement in technology, optical methods are playing important role for rapid, real-time, non-destructive and accurate detection of meat quality parameters. Near-infrared method and hyperspectral imaging method are important methods for non-destructive measurement of beef tenderness. This study focused on the application of hyperspectral image analysis for non-destructive detection of beef tenderness at different points of the sample. Considering the measurement complexity due to complex beef structure as well as the disadvantage of near infrared spectrum for single point detection, this study made use of hyperspectral imaging system to obtain three-dimensional information from each sample. Fifty-six beef samples were obtained from the slaughter house Yuxiangyuan in Beijing and were cut into 3 cm thick slices, vacuum packaged and then stored in 4°C environment before hyperspectral image acquisition. Reflectance spectrum was obtained for each sample from acquired images. Stepwise regression and genetic algorithm (GA) were used to identify the feature wavelengths, thus reducing the high dimensionality of the hyperspectral data. Eight feature wavelengths were selected, which were used to develop prediction model for measuring the shear force value at each point in the sample. By the principal component analysis (PCA), every sample could acquire 5 PCA images. Gray level co-occurrence matrix (GLCM) was applied to extract 8 main texture parameters from the characteristic band image and the 3 PCA images. Eight wavelengths were extracted from these 8 texture characteristic parameters respectively, with a total of 64 texture variables. Also, from five PCA images 40 texture variables were extracted. These parameters were used to establish a model based on linear discrimination analysis (LDA) and support vector machine (SVM) for beef tenderness. Because the number of principal components has a greater impact on the accuracy of discriminant model, before the training of SVM model, it first needed to select the appropriate number of principal components. Finally, three PCA images which included 95.37% information of every sample were chosen to extract texture parameters. With texture parameters of band images, the prediction set's accuracy of the discriminant model was 88.89%. There had some shortcomings that on one hand, the band images had great influence on the result, and on the other hand, some information may be missed with selected band images, so the texture features of the image of sample main component were used to establish classification model. After analysis and comparison, the accuracy of main component model was 94.44%, which was higher than that of band image model. In addition, the LDA method was more applied to establish classification model than SVM method. The results show that the image texture features can determine the distribution of beef tenderness. The results can provide the theoretical reference for the research on rapid non-destructive detection technique of beef tenderness. [ABSTRACT FROM AUTHOR]

An intelligent fruit and vegetable recognition system utilizing image recognition can accurately and rapidly indentify different kinds of fruits and vegetables, which can improve supermarket and market sales efficiency. The feature extracting method is a very important issue in an intelligent fruit and vegetable recognition system. However, traditional fruit and vegetable recognition algorithms either ignore the texture feature of fruits and vegetables, or used texture features that couldn't better represent the texture of fruit and vegetable images. In order to represent the texture feature of fruit and vegetable images better and improve the intelligent fruit and vegetable recognition system recognition rate, we proposed a novel texture feature extraction algorithms called color completed local binary pattern (CCLBP) in this paper. By extracting different kinds of color channels completed by a local binary pattern (CLBP) texture feature, the CCLBP constructed a new texture feature extraction algorithm. The Fruit and vegetable recognition system model uses CCLBP to extract an image texture feature, and uses a HSV color histogram and Border/interior pixel classification (BIC) color histogram to extract image color features. Then it uses a matching score fusion algorithm to fuse color and texture features, and finally, a nearest neighbor (NN) classifier is used to realize fruit and vegetable recognition. To verify the effectiveness of the algorithms, two different fruit and vegetable databases, called an interior database and an outdoor database, were constructed in this paper. The interior database acquired in a laboratory contains 13 kinds of fruits and vegetables, which is used to verify algorithms recognition performance under different kinds of illumination. The outdoor database acquired in the market contains 47 kinds of fruits and vegetables, which is used to verify algorithms recognition performance under a different number of training sets. A Fruit and vegetable recognition experiment under different kinds of illumination showed that, only by the texture feature indentifying the kinds of fruits and vegetables, the recognition rate of the CCLBP was 5% higher than the traditional fruit and vegetable texture features (such as Unser, TestA), which means that the CCLBP is more suitable for fruit and vegetable recognition; besides, compared with other texture algorithms, the CCLBP fused with HSV color histogram and BIC color histogram can achieve a 73.93% highest mean recognition rate, which takes about 1.1 seconds indentifying an image. A fruit and vegetable recognition experiment under a different number of training sets had similar results as the experiment under different kinds of illumination. The recognition rate of the CCLBP was still higher than the traditional fruits and vegetables texture features. What's more, the CCLBP fused with a HSV color histogram and a BIC color histogram can achieve 94.26%, the highest recognition rate. The experiments under different kinds of illumination and under different number of fruits and vegetables confirm the feasibility of our algorithm. Our algorithm can be used in intelligent fruit and vegetable recognition system, which improves the system accuracy rate. [ABSTRACT FROM AUTHOR]

Technologies that can efficiently identify citrus diseases would assure fruit quality and safety and minimize losses for citrus industry. This research was aimed to investigate the potential of using color texture features for detecting citrus peel diseases. A color imaging system was developed to acquire RGB images from grapefruits with normal and five common diseased peel conditions (i.e., canker, copper burn, greasy spot, melanose, and wind scar). A total of 39 image texture features were determined from the transformed hue (H), saturation (S), and intensity (I) region-of-interest images using the color co-occurrence method for each fruit sample. Algorithms for selecting useful texture features were developed based on a stepwise discriminant analysis, and 14, 9, and 11 texture features were selected for three color combinations of HSI, HS, and I, respectively. Classification models were constructed using the reduced texture feature sets through a discriminant function based on a measure of the generalized squared distance. The model using 14 selected HSI texture features achieved the best classification accuracy (96.7%), which suggested that it would be best to use a reduced hue, saturation and intensity texture feature set to differentiate citrus peel diseases. Average classification accuracy and standard deviation were 96.0% and 2.3%, respectively, for a stability test of the classification model, indicating that the model is robust for classifying new fruit samples according to their peel conditions. This research demonstrated that color imaging and texture feature analysis could be used for classifying citrus peel diseases under the controlled laboratory lighting conditions. [ABSTRACT FROM AUTHOR]

Computer‐aided diagnosis (CAD) is a common tool for the detection of diseases, particularly different types of cancers, based on medical images. Digital image processing thus plays a significant role in the processing and analysis of medical images for diseases identification and detection purposes. In this study, an efficient CAD system for the acute lymphoblastic leukaemia (ALL) detection is proposed. The proposed approach entails two phases. In the first phase, the white blood cells (WBCs) are segmented from the microscopic blood image. The second phase involves extracting important features, such as shape and texture features from the segmented cells. Eventually, on the extracted features, Naïve Bayes and k‐nearest neighbour classifier techniques are implemented to identify the segmented cells into normal and abnormal cells. The performance of the proposed approach has been assessed through comprehensive experiments carried out on the well‐known ALL‐IDB data set of microscopic blood images. The experimental results demonstrate the superior performance of the proposed approach over the state‐of‐the‐art in terms of accuracy rate in which achieved 98.7%. [ABSTRACT FROM AUTHOR]

Since histopathological images exist in various forms, performing segmentation on these images is tedious. While in cancer‐free colon tissue, epithelial cells generally have an elliptical shape; their structure alters in a malignant tissue. This study proposes a technique consisting of colon biopsy image segmentation and a hybrid set of features for classification, and is evaluated on multiple databases with various levels of magnifications. This study presents a novel image segmentation method with multi‐level thresholding based on Rényi's two‐dimensional entropy with a cultural algorithm (2DReCA). Based on the entropy, elliptical epithelial cells, being the region of interest, are identified from the segmented background. After successful segmentation, shape descriptors are extracted with morphological operations. Two sets of texture features (grey‐level co‐occurrence matrix and block‐wise elliptical local binary pattern) are calculated based on pre‐processed grey‐scale colon images. The proposed hybrid feature vector set, then concatenates the extracted features for training and testing with a random forest classifier. The proposed segmentation and classification model is evaluated by considering four data sets consisting of various colon images at different magnifications. In addition, it is evaluated by multiple performance measures and compared with existing techniques. [ABSTRACT FROM AUTHOR]

Since histopathological images exist in various forms, performing segmentation on these images is tedious. While in cancer-free colon tissue, epithelial cells generally have an elliptical shape; their structure alters in a malignant tissue. This study proposes a technique consisting of colon biopsy image segmentation and a hybrid set of features for classification, and is evaluated on multiple databases with various levels of magnifications. This study presents a novel image segmentation method with multi-level thresholding based on Rényi's two-dimensional entropy with a cultural algorithm (2DR $_e$e CA). Based on the entropy, elliptical epithelial cells, being the region of interest, are identified from the segmented background. After successful segmentation, shape descriptors are extracted with morphological operations. Two sets of texture features (grey-level co-occurrence matrix and block-wise elliptical local binary pattern) are calculated based on pre-processed grey-scale colon images. The proposed hybrid feature vector set, then concatenates the extracted features for training and testing with a random forest classifier. The proposed segmentation and classification model is evaluated by considering four data sets consisting of various colon images at different magnifications. In addition, it is evaluated by multiple performance measures and compared with existing techniques. [ABSTRACT FROM AUTHOR]

Mammography is a very useful tool to diagnose breast cancer in early stages when it is easier to treat. There are two types of evidence that radiologists look for in a mammogram, calcifications and the existence of masses. In this study, an intelligent computer‐aided diagnosis system is proposed for the detection of masses in mammographic images regardless of their nature. The proposed method uses a combination of extended maxima transformations, having different threshold values, in order to find suitable internal and external markers for a marker‐based watershed segmentation. After segmentation, a two‐stage classifier is used to distinguish the masses better from the healthy breast tissue. A feature vector based mainly on contrast and texture features is calculated and two alternative approaches, a Bayesian classifier and a support vector machine (SVM) with Gaussian kernel function, are implemented for further reduction of the false positive areas. The system was evaluated using the data from two online databases. Specifically, 73 mammographic images from the new curated breast imaging subset of digital database for screening mammography (CBIS‐DDSM) database and all the mammographic images that contain masses from the mini‐mammographic image analysis society (MIAS) database were used. The overall sensitivity, in both datasets, was near 80% when the Bayesian classifier was used and above 85% when the SVM was applied. [ABSTRACT FROM AUTHOR]

• For Gabor, gradient, HOG and wavelet features the number of intensity levels minimally affects the classification. • Normalization method and number of intensity levels influence the classification for GLCM and GRLM features. • For MRI and CT images, the lowest classification error is usually obtained with a large number of intensity levels. • For MRI and CT images, the recommended normalization method is 1%–99%. • For images with additive noise and GLCM or GRLM features, ±3σ normalization and low number of grey levels is recommended. Image texture is a very important component in many types of images, including medical images. Medical images are often corrupted by noise and affected by artifacts. Some of the texture-based features that should describe the structure of the tissue under examination may also reflect, for example, the uneven sensitivity of the scanner within the tissue region. This in turn may lead to an inappropriate description of the tissue or incorrect classification. To limit these phenomena, the analyzed regions of interest are normalized. In texture analysis methods, image intensity normalization is usually followed by a reduction in the number of levels coding the intensity. The aim of this work was to analyze the impact of different image normalization methods and the number of intensity levels on texture classification, taking into account noise and artifacts related to uneven background brightness distribution. Analyses were performed on four sets of images: modified Brodatz textures, kidney images obtained by means of dynamic contrast-enhanced magnetic resonance imaging, shoulder images acquired as T2-weighted magnetic resonance images and CT heart and thorax images. The results will be of use for choosing a particular method of image normalization, based on the types of noise and distortion present in the images. [ABSTRACT FROM AUTHOR]

Shape and texture features provide a novel framework for expression recognition by using salient landmarks based triangle initialisation and identification of texture regions. Detection of effective landmarks is achieved by well‐known appearance‐based model to form a grid. Accordingly, several triangles are identified within the grid with respect to the nose landmark reference point. These salient landmarks are also used to find the texture regions. Normalised shape and texture signatures are derived from triangles and texture regions. Stability indices are determined from shape and texture signatures which are also exploited as significant features for recognition of facial expressions. Statistical measures such as range, moment, skewness, kurtosis, and entropy are used to supplement the feature set. Individual and combined features are fed into multilayer perceptron and deep belief network (DBN) network to classify different expression categories encompassing anger, sadness, fear, disgust, surprise, and happiness. The authors investigated the performance of their proposed system on Cohn–Kanade, JAFFE, MMI, MUG, and Wild face benchmark databases. Thorough experimentation establishes the performance superiority of the proposed methodology over other existing competitors. Combining features is also validated through extensive results and analyses. [ABSTRACT FROM AUTHOR]

The authors propose a novel‐makeup detection approach that assists face recognition systems to achieve a higher‐accuracy rate while dealing with makeup images. Makeup features are defined in this work using biologically inspired features (BIFs). To establish makeup depictive features more specifically, colour and texture features are essential to be extracted from images. Hence, they create makeup depictive features in the last complex layer of BIFs (C2) as average skin tone (AST) and a histogram of oriented gradient (HOG), where AST is representative of colour and HOG exhibits texture. The proposed makeup BIFs are extracted from grayscale images and instead of breaking the face image into several patches, the whole face image is employed. This resulted in the performance acceleration as well as higher accuracy rate compared with state‐of‐the‐art makeup detection schemes. Subsequently, they employ a machine learning scheme to train the makeup detection system by feeding it makeup and non‐makeup labelled images. They exploit the correlation‐based method for the face recognition system and compare the results with the direct two‐dimensional principal component analysis face recognition scheme for makeup datasets. Experimental results show the highest accuracy rate of 97.07% was achieved by the proposed algorithm for face recognition system considering makeup. [ABSTRACT FROM AUTHOR]

Purpose: To develop a new algorithm to measure the similarity between the query lung mass and reference lung mass data set for content-based medical image retrieval (CBMIR). Methods: A lung mass data set including 746 mass regions of interest (ROIs) was assembled. Among them, 375 ROIs depicted malignant lesions and 371 depicted benign lesions. Each mass ROI is represented by a vector of 26 texture features. A kernel function was employed to map the original data in input space to a feature space. In this space, a semisupervised distance metric was learned, which used differential scatter discriminant criterion to represent the semantic relevance, and the regularization term to represent the visual similarity. The learned distance metric can measure the similarity of the query mass and reference mass data set. The clustering accuracy is used to configure the parameters. The retrieval accuracy and classification accuracy are used as the performance assessment index. Results: After configuring the parameters, a mean clustering accuracy of 0.87 can be achieved. For retrieval accuracy, our algorithm achieves better performance than other state-of-the-art retrieval algorithms when applying a leave-one-out validation method to the testing data set. For classification accuracy, the area under the ROC curve of our algorithm can be achieved as 0.941±0.006. The running times of 346 query images with the proposed algorithm are 5.399 and 6.0 s, respectively. Conclusions: The study results demonstrated the proposed algorithm outperforms the compared algorithms, when taking the semantic relevant and visual similarity into account in kernel space. The algorithm can be used in a CBMIR system for a query mass to retrieve similarity masses, which can help doctors make better decisions. [ABSTRACT FROM AUTHOR]

This work presents an approach for combining texture and shape feature sets towards age‐invariant face recognition. Physiological studies have proven that the human visual system can recognise familiar faces at different ages from the face outline alone. Based on this scientific fact, the phase congruency features for shape analysis were adopted to produce a face edge map. This was beneficial in tracking the craniofacial growth pattern for each subject. Craniofacial growth is common during childhood years, but after the age of 18, the texture variations start to show as the effect of facial aging. Therefore, in order to handle such texture variations, a variance of the well‐known local binary pattern (LBP) texture descriptor, known as LBP variance was adopted. The results showed that fusing the shape and the texture features set yielded better performance than the individual performance of each feature set. Moreover, the individual verification accuracy for each feature set was improved when they were transformed to a kernel discriminative common vectors presentation. The system achieved an overall verification accuracy of above 93% when it was evaluated over the FG‐NET face aging database. [ABSTRACT FROM AUTHOR]

Purpose: To help improve efficacy of screening mammography by eventually establishing a new optimal personalized screening paradigm, the authors investigated the potential of using the quantitative multiscale texture and density feature analysis of digital mammograms to predict near-term breast cancer risk. Methods: The authors' dataset includes digital mammograms acquired from 340 women. Among them, 141 were positive and 199 were negative/benign cases. The negative digital mammograms acquired from the "prior" screening examinations were used in the study. Based on the intensity value distributions, five subregions at different scales were extracted from each mammogram. Five groups of features, including density and texture features, were developed and calculated on every one of the subregions. Sequential forward floating selection was used to search for the effective combinations. Using the selected features, a support vector machine (SVM) was optimized using a tenfold validation method to predict the risk of each woman having image-detectable cancer in the next sequential mammography screening. The area under the receiver operating characteristic curve (AUC) was used as the performance assessment index. Results: From a total number of 765 features computed from multiscale subregions, an optimal feature set of 12 features was selected. Applying this feature set, a SVM classifier yielded performance of AUC= 0.729±0.021. The positive predictive value was 0.657 (92 of 140) and the negative predictive value was 0.755 (151 of 200). Conclusions: The study results demonstrated a moderately high positive association between risk prediction scores generated by the quantitative multiscale mammographic image feature analysis and the actual risk of a woman having an image-detectable breast cancer in the next subsequent examinations. [ABSTRACT FROM AUTHOR]

Writer verification methods from handwriting images have been widely used in biometrics, forensic casework and so on. However, their performance conducted by a computer is still far behind that of human beings. This study proposes an offline writer verification method which uses a new hybrid feature. The characteristics of this new feature are the combination of shape and pen pressure information. For shape information, the authors use the weighted direction code histogram, which is often used in Japanese handwriting recognition and writer verification methods. For pen pressure information, the authors use the texture features of infrared (IR) images obtained from a multi‐band image scanner. Although the simple use of pen pressure information encoded in the IR image cannot improve the geometric mean (g‐mean)‐based error rate, the use of clipping process and second‐order statistics can decrease the g‐mean‐based error rate from 4.8 to 3.2%. [ABSTRACT FROM AUTHOR]