Search

In case of illumination change, the local binary pattern (LBP) descriptor have found to be used in analysis of texture of the image because of the ease of computation and robustness to such changes. However, the LBP technique also comes with limitations such as its inability to capture the discriminative information completely. For enhancing the LBP's performance, we proposed a new texture descriptor for rotation, illumination and scale invariance (IRSLBP) for texture classification. The proposed approach extracts the color features through quantification of the RGB space into single channel, which is marked by a smaller number of shades to reduce computation and to improve the efficiency. The IRSLBP descriptor provides the scale invariance by considering the circular neighbor set of every central pixel other than the normal neighboring pixels. Moreover, the proposed IRSLBP decomposed the difference vector into sign part and magnitude part by local difference sign magnitude transform. In addition, these mitigated the influence of rotation, illumination or noise and demonstrated effective robustness. Using the proposed IRSLBP descriptor, we have classified the different textures using Multi kernel support vector machine (SVM) approach. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a new texture image retrieval method based on discrete non-separable shearlet transform (DNST) domain local neighborhood intensity pattern (LNIP), which can fully characterize the discriminative information among particular coefficient and its adjacent neighbors within a local window. Firstly, the original image is decomposed into different subbands of frequency and orientation responses by using discrete non-separable shearlet transform (DNST). Secondly, based on center symmetric-local binary pattern theory, the sign and magnitude patterns of DNST domain LNIP descriptor are constructed using novel computation rule. Meanwhile, a new binary bit-string encoding scheme is developed, which can overcome the information redundant and inaccurate problem of conventional encoding strategy in LNIP. Thirdly, the mean, standard deviation and entropy values of the DNST domain LNIP at different scales are calculated and fused into a vector as the image texture feature values, which effectively reduce the feature dimensions. And finally, image similarity measurement is accomplished by using closed-form solutions for the Kullback–Leibler divergences between the DNST domain LNIP based image texture features. Experimental results on some test images and comparison with well-known existing methods demonstrate the efficacy and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

At present, most of the existing image inpainting methods can not reconstruct the reasonable structure of the image, especially when the important part of the image are missing. Some methods focus on reconstructing a continuous and reasonable structure between the missing area and the undamaged area, but when restoring the image texture, it will generate a fuzzy texture inconsistent with the surrounding area. In order to make the inpainted image have continuous structure and vivid texture, a three-stage model is proposed in this paper: in the first stage, the edge generator is trained by using the edge map of the image to inpaint the input missing edge structure; in the second stage, the predicted edge structure map is used as a guide, and the smooth image is used to train the structure reconstructor to complete the overall structure of the image; in the third stage, based on the reconstructed structure, the texture generator using appearance flow operation is used to generate the texture details of the image. We have conducted experiments on multiple datasets. Compared with the state-of-the-art methods, the repaired images using our method have more reasonable structure and vivid texture,and our method has better performance. [ABSTRACT FROM AUTHOR]

Local binary pattern (LBP) has already been proved to be a powerful measure of image texture with fixed sampling scheme: all P neighbor pixels in a single-scale are usually sampled by using a fixed radius R. It can effectively address grayscale and rotation variations. However, the LBP method is sensitive to image noise and fails to achieve desirable performance for texture classification with significant scale changes. With the aim to deal with these disadvantages of LBP, a new method named scale-adaptive local binary pattern (SALBP) is proposed in this paper. The essence of our proposed SALBP method is to adaptively find a single but optimal scale from multiple scales for each radial direction in accordance with the characteristics of a local area. First, we select candidates of neighbors by the majority vote strategy for signs. Second, we determine final neighbor pixels by the maximal difference magnitude selection strategy for magnitudes of candidates. This procedure lets each neighbor pixel to adaptively obtain its own optimal scale from multiple scales, which refers to the adaptive optimal sampling radius. Therefore, scale invariance can be significantly improved. Extensive experiments on four public texture databases (i.e., Outex, CUReT, UIUC and Brodatz) demonstrate that the proposed SALBP method achieves significantly better results than representative LBP variants for texture classification tasks with a smaller feature dimension. [ABSTRACT FROM AUTHOR]

An image descriptor, multi-channel local oblique symmetry texture pattern (MLOSTP), has been introduced for image retrieval. To capture color, texture, and local spatial information in different channels, three cross-channels, including RV, GV, and BV, are adopted through the combination of RGB with HSV. In each cross-channel, two meaningful local difference maps are introduced between center pixels and surrounding pixels according to their gray differences, which results in more local pixel variations. Based on the maps, two oblique symmetry texture patterns are derived. Not only is the difference between the two color channels explored, but the diagonal asymmetry information of the image is also incorporated into the local patterns. Furthermore, the spatial structure information between different spectral channels is considered. The performance of MLOSTP is estimated by several experiments on four databases. The results show that MLOSTP can achieve better performance than other descriptors. [ABSTRACT FROM AUTHOR]

Local binary pattern is one of the most known descriptors, which is used for texture classification. Although completed local binary pattern is seemingly the most precise variant of this type of descriptor and provides high classification accuracy by joining three histograms of features. Merging these histograms increases the features number significantly. To reduce the size of features, in this paper, some mapping methods are proposed for feature reduction and mapping of these features into a histogram. All of the proposed mapping methods are rotation and illumination invariant. Furthermore, a constraint feature selection method is proposed that selects discriminative features. Applying the introduced methods to the known benchmarks like Outex (TC3, TC10, TC13, TC12(t) and TC12(h)), UIUC, CUReT and Defect Fabric datasets indicates that even by adopting lower number of features, the classification rate is enhanced from 1% to 9% while the features number are decreased around 10% to 99%. Comparison results on the same datasets imply the superiority of the proposed schemes to the conventional methods. [ABSTRACT FROM AUTHOR]

Recent advances in Generative Adversarial Network (GAN) have made it considerably easy to generate photo-realistic images. However, when GAN-synthesized face images are used maliciously, they will lead to severe moral, ethical, and legal issues. To expose GAN-generated face images, most existing works rely heavily on deep models, which are costly and time-consuming. In this work, we propose a blind approach to detect GAN-generated face images by handcrafted features. Due to the differences of the inherent formation mechanism, nature and GAN-generated face images exhibit different texture and sensor noises, which are exploited as the clues to expose the GAN-generated face images. Specifically, uniform local binary pattern (LBP) features from real face and generated face images, and extract subtractive pixel adjacency matrix (SPAM) features in their sensor noises. Both features are fed to support vector machine (SVM) classifier to verify the authenticity of the face images. The result shows that our proposed approach can successfully detect GAN-generated fake face images with an accuracy up to 97.60%. Furthermore, it can distinguishing the fake face images generated by different GANs. [ABSTRACT FROM AUTHOR]

Medical image analysis plays a very indispensable role in providing the best possible medical support to a patient. With the rapid advancements in modern medical systems, these digital images are growing exponentially and reside in discrete places. These images help a medical practitioner in understanding the problem and then the best suitable treatment. Radiological images are very often found to be the critical constituent of medical images. So, in health care, manual retrieval of visually similar images becomes a very tedious task. To address this issue, we have suggested a content-based medical image retrieval (CBMIR) system that effectively analyzes a Radiological image's primitive visual features. Since radiological images are in gray-scale form, these images contain rich texture and shape features only. So, we have suggested a novel multi-resolution radiological image retrieval system that uses texture and shape features for content analysis. Here, we have employed a multi-resolution modified block difference of inverse probability (BDIP) and block-level variance of local variance (BVLC) for shape and texture features, respectively. Our proposed scheme uses a multi-resolution and variable window size feature extraction strategy to maintain the block-level co-relation and extract more salient visual features. Further, we have used the MURA x-ray image dataset, which has 40561 images captured from 12173 different patients to demonstrate the proposed scheme's retrieval performance. We have also performed and compared image retrieval experiments on Brodatz and STex texture, Corel-1K, and GHIM-10K natural image datasets to demonstrate the robustness and improvement over other contemporaries. [ABSTRACT FROM AUTHOR]

In this paper, an extended complete LBP (ELBP) for texture classification is proposed, in which the local feature vectors are composed of the ratio of the central pixel and its neighborhood pixels to a specific threshold. ECLBP_C represents the gray level of the image, which is obtained by comparing the center pixel with the global threshold. ECLBP_S and ECLBP_M represent the symbol component and the magnitude component of the 3-neighbor region of the center pixel respectively, which are obtained by calculating two binary codes using the original LBP algorithm for the 3-neighbor region of the center pixel. In order to make the proposed algorithm scalable, in addition to the 3-neighbor pixels of the central pixel, the proposed algorithm use the center pixel as the center, r as the radius in the circle with ɑ as the filter's radius to generate extended binary coding, such as ECLBP_ES_r,α ECLBP_EM_ r,α. In order to describe the local region feature vector in detail, specified ECLBP_ES_r,α and ECLBP_EM_r,α can be obtained by defining the number of extensions according to actual needs, and then established and concatenated all ECLBP gray histograms for statistics. In the experimental part, we analyze the performance of the proposed algorithm in detail, and prove that the algorithm has good scalability and robustness. The experimental results show that the classification accuracy of the proposed algorithm is up to 99% after 3 expansions in Table 2. The source codes of the proposed algorithm can be downloaded from https://github.com/zenqiang/ECLBP.git. [ABSTRACT FROM AUTHOR]

Today, large amount of data are stored in image format. Content based image retrieval from bulk databases has become an interesting research topic in last decade. Most of the recent approaches use joint of texture and color information. In most cases, the color and texture features are concatenated together and equal importance is given to each one. The human visual system, usually pays more attention to the textural properties of objects to recognize. In this paper a new approach is proposed for content based image retrieval based on weighted combination of color and texture features. Firstly, to achieve discriminant features, texture features are extracted using modified local binary patterns (MLBP) and local neighborhood differences patterns (LNDP) and filtered gray level co-occurrence matrix (GLCM). Also, quantization color histogram is used to extract color features. Next, the similarity matching is performed based on canbera distance in color and texture features separatly. Finally, a weighted decision is performed to retrieve most similar database images to the user query. The performance of the proposed approach is evaluated on Corel 1 K and Corel 10k datasets. Results show that proposed approach provide better performance than state-of-the-art methods in terms of precision and recall rate. [ABSTRACT FROM AUTHOR]

Statistical models of transform coefficients are an efficient way to discriminate between texture classes. Statistical-based approaches provide a natural way to solve texture retrieval problem. In this paper, we proposed a new framework for textured image retrieval in DD-DTCWT (Double-density dual-tree complex wavelet transform) domain, which is based on the mixture of Cauchy and Vonn statistical models. Firstly, the image is decomposed into frequency subbands using DD-DTCWT, and the amplitude and relative phase of DD-DTCWT coefficients are computed. Secondly, Cauchy and Vonn distributions are employed respectively to capture the statistical characteristics of the magnitude and relative phase of DD-DTCWT coefficients, and the Cauchy and Vonn model parameters are utilized to construct a compact texture image feature space. Finally, image similarity measurement is accomplished by using closed-form solutions for the Kullback–Leibler divergences between the Cauchy and Vonn statistical models. Experimental results demonstrate the high efficiency of our textured image retrieval scheme, which can provide better retrieval rates and lower computational cost, in comparison with the state-of-the-art approaches recently proposed in the literature. [ABSTRACT FROM AUTHOR]

Imaging techniques like computed tomography (CT) and ultrasound are employed to provide valuable information for physicians, including size, contour, and internal organs' anatomical information. Information retrieval systems can be used to deliver on-time information to the radiologists when some sections of scans are lost. In this study, a new content-based image retrieval (CBIR) model based on an effective combination of color, texture, and shape features is proposed to reconstruct these images' corrupted portions. For this purpose, image scans are normalized, and their noise is reduced by employing a median filter. Then, the color channel shift is modified utilizing the Simple Linear Iterative Clustering (SLIC) superpixel. Afterward, a Histogram of Oriented Gradients (HOG) descriptor is introduced to enhance image contrast and feature extraction. Finally, local thresholding based on Local Binary Patterns (LBP) is performed to separate the image details into three components to examine the light and edge intensity. The proposed method is experimented on several images by evaluating the texture, color, and shape morphology of the reconstructed images compared to the ground truth. The highest content retrieval rate of 90.54% on a liver CT scan image demonstrates the proposed method's efficiency compared with former state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Image processing is a very rich and important research area, which provides efficient solutions to many real and industrial problems. Texture analysis is one of the most interesting fields in image processing and pattern recognition. It became a very attractive research area these last years, especially after the growth and the advancement of technologies. This paper deals with texture analysis and unsupervised texture segmentation problem. The goal of this study is to develop a new segmentation method based on the textural features of the images. The proposed system is composed of different steps. First, the image is analyzed in each pixel using the Gray Level Co-occurrence Matrix (GLCM) feature extraction method. Four Haralick parameters (Haralick Proc IEEE 67(5):786–804, 16) are calculated and represented in four matrix. After that, we applied the gradient to detect edges from the extracted images. In order to localize the area of the discontinuity of the texture, we proposed a new method for joining the edge and region growing. The proposed system is applied on several textured images and the obtained results are shown in the experimentation section. A number of experiments have been done with randomly generated textured images. The experiments have shown the efficiency of the proposed method compared to other existing methods and its robustness to enhance the segmentation precision of textured images. [ABSTRACT FROM AUTHOR]

Depth-image-based rendering is an efficient way to produce content for 3D video and free viewpoint video. However, since the background that is occluded by the foreground objects in the reference view may become visible in the synthesized view, disocclusions are produced. In this paper, a disocclusion-type aware hole filling method is proposed for disocclusion handling. Disocclusions are divided into two types based on the depth value of their boundary pixels: foreground-background (FG-BG) disocclusion and background-background (BG-BG) disocclusion. For FG-BG disocclusion, the depth values of the associated pixels are optimized in the reference image to ensure the removal of ghosts and adaptively divide the disocclusion into some small holes. For BG-BG disocclusion, a foreground removal method is applied to remove the corresponding foreground objects. The removed regions are filled with the surrounding background textures so that the BG-BG disocclusion in the synthesized image can be eliminated. Experimental results indicate that the proposed method outperforms the other methods in the objective and subjective evaluations. [ABSTRACT FROM AUTHOR]

Methods based on locally encoded image features have recently become popular for texture classification tasks, particularly in the existence of large intra-class variation due to changes in illumination, scale, and viewpoint. Inspired by the theories of image structure analysis, this work proposes an efficient, simple, yet robust descriptor namely local jet pattern (Ljp) for texture classification. In this approach, a jet space representation of a texture image is computed from a set of derivatives of Gaussian (DtGs) filter responses up to second order, so-called local jet vectors (Ljv), which also satisfy the Scale Space properties. The Ljp is obtained by using the relation of center pixel with its' local neighborhoods in jet space. Finally, the feature vector of a texture image is formed by concatenating the histogram of Ljp for all elements of Ljv. All DtGs responses up to second order together preserves the intrinsic local image structure, and achieves invariance to scale, rotation, and reflection. This allows us to design a discriminative and robust framework for texture classification. Extensive experiments on five standard texture image databases, employing nearest subspace classifier (Nsc), the proposed descriptor achieves 100%, 99.92%, 99.75%, 99.16%, and 99.65% accuracy for Outex_TC10, Outex_TC12, KTH-TIPS, Brodatz, CUReT, respectively, which are better compared to state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The main focus of this paper is to improve the performance of the texture model Optimized Local Ternary Patterns (OLTP), which is known as one of the successful variants of the texture model Local Binary Patterns (LBP), a well known method for texture analysis and its applications. Generally preprocessing is used in digital image processing for reducing the unwanted noise and disturbances in such a way that it improves the quality of the image. Preprocessing not only removes the distortions but also enhances the features of the image for further processing. To achieve better recognition accuracy, the texture model OLTP was combined with a preprocessing method that uses nonlinear diffusion method as a preprocessing tool in this paper, with the hope that this idea will surely improve the local feature description and texture classification process. This nonlinear diffusion method uses two newly developed edge stopping functions for preprocessing. This proposed method is tested with two standard texture datasets namely Brodatz Dataset and Usptex dataset. The results show that the use of the preprocessing step really improved the texture classification accuracy. [ABSTRACT FROM AUTHOR]

In recent time, most of the steganographic methods minimize the embedding cost while maximizing the embedding capacity by injecting message bits in the highly textured regions of the image. Recently, the Clustering Modification Direction (CMD) steganography has been proposed as a wrapper over the additive steganography algorithms, resulting in a substantial improvement in statistical imperceptibility against state-of-the-art steganalytic classifiers. In this paper, a steganalysis scheme, named Selective-Signal-Removal (SSR) is proposed to mount an attack on the CMD algorithm. It has been observed experimentally that the CMD scheme has a tendency to embed in a localized cluster having higher texture. The proposed scheme exploits this fact and tries to predict the embedding zones. It essentially discards the irrelevant region of the image (which may not be modified by the CMD algorithm while embedding) by using a heuristic function with an assignment algorithm to improve the steganalytic detection rate. The experimental results show that the proposed SSR scheme can detect CMD based steganography with improved accuracy. [ABSTRACT FROM AUTHOR]

Texture characterization and identification is a key issue for a variety of computer vision and image processing applications. Current techniques developed for dealing with the purpose thereof still present performance issues when applied in the presence of noise, owing to the intrinsic properties of the image being analyzed can not be maintained. Based on the principle that data distribution of these textures form a non-deterministic complex system, mathematical tools can help to characterize them. In this paper, we propose new approaches capable of quantifying such intrinsic properties by means of the Fisher information matrix. The methodology consists in firstly defining each wavelet sub-band of the texture image as a complex system modeled by a Gaussian Markov Random Field and secondly computing their respective Fisher information matrix and Shannon entropy. Applying the proposed texture descriptor to Salzburg and Outex datasets revealed a significant superiority of the proposed method vis-à-vis the majority of traditional and novel texture descriptors presented in the literature. [ABSTRACT FROM AUTHOR]

This paper proposes a secure binary image steganography by minimizing the flipping distortion on the statistics of local texture pattern (LTP) and constructing flexible carriers of syndrome-trellis code (STC). Firstly, the change of LTP's statistic caused by flipping one pixel is employed to measure the flipping distortion of the corresponding pixel, which can well describe the flipping distortion on both statistics and vision. Secondly, we select the non-uniform blocks flexibly and reconstruct them as STC's carriers, which can access a scalable and nearly continuous capacity upper bound to accommodate to the different secret message lengths. Our experimental results show that, for one specific message length, the security on both statistics and vision is improved significantly when the message length is closed to the capacity upper bound. The comparisons with previous steganographic schemes demonstrate the superiority of the proposed scheme. [ABSTRACT FROM AUTHOR]

In order to realize the retrieval efficiency and detection precision of digital library collection resources, a new clustering algorithm (Fast density peak clustering,FDPC) based on fast texture density peak is proposed. Firstly, a framework of document image retrieval based on content description is given, based on median filter and direct-square equalization strategy, denoising and background processing of input document image are introduced, then density peak clustering (DPC) is used to classify image, and the convergence performance of DPC algorithm is improved by using dynamic truncation distance mode. Finally, based on the library standard test library (Corel), the performance of the proposed algorithm is validated experimentally, and the experimental results show that the proposed method has higher retrieval efficiency and retrieval accuracy. [ABSTRACT FROM AUTHOR]

In aims to ensure images authentication, this paper proposes a blind spatial domain-based image watermarking using texture analysis and association rules mining. The idea is to identify the strongly textured locations in the host image for inserting the watermark. Indeed, texture is correlated with the Human Visual System (HVS). It can therefore be helpful in designing a watermarking approach to enhance the imperceptibility and the robustness. Here a solution is proposed in which four gray-scale histogram based-image features (DC, skewness, kurtosis, and entropy) are chosen as input data for designing association rules. Subsequently, the Apriori algorithm is applied to mine the relationships between the selected features. The higher significant relationships between the selected features are used to identify the strongly textured blocks for watermark embedding. Two strong parameters (lift and confidence) computed using association rules mining were used to design a means of blind watermarking. The experimental results show that interesting ratios of imperceptibility, robustness and embedding rate with low execution time can be obtained by this approach. [ABSTRACT FROM AUTHOR]

Based on X-ray image of tire with periodic texture, this paper proposes an algorithm of detecting joint in #0 belt. Firstly, by projecting #0 belt image at 45° direction, we divide #0 belt image into several blocks with the same size based on periodic texture. Then, we find out the block containing joint and locate its upper and lower boundaries. Finally, upper and lower boundaries of joint are located by comparing the block containing joint with its corresponding standard block. The standard block is one of segmented blocks in first step. We quantify joint defects in #0 belt (large joint, small joint or appropriate joint), and experimental results show that our algorithm can accurately locate the joint and quantify the size of joint with 3.4% false positive rate and 2% false negative rate, which meets the industrial requirements. [ABSTRACT FROM AUTHOR]

Local binary patterns (LBP) has been successfully applied to several tasks in computer vision due to its efficacy and computational simplicity. LBP can be computed in different neighborhoods to derive multi-scale LBP (MS-LBP) for performance enhancement. In MS-LBP, different scales LBP histograms are either combined in a concatenate way assuming that different scales LBP are independent, or jointly combined to generate a multi-dimensional histogram. However, the independence assumption does not hold so that the cross-scale information is lost in concatenate MS-LBP, while joint MS-LBP suffers high feature dimension. Then, to deal with the independence assumption and better exploit multi-scale information, a new texture descriptor called decorrelated local binary patterns (dLBP) is proposed in this paper. Unlike traditional MS-LBP schemes, discrete cosine transform (DCT) is firstly applied as a decorrelation transform to different scales differences to derive independent patterns. Then, the histograms corresponding to each pattern are concatenated as a new texture descriptor. Besides, the decorrelated magnitude components are also utilized to further enhance the performance. Experimental results show that the proposed dLBP features outperform both the concatenate MS-LBP and some recent state-of-the-art schemes for texture classification. [ABSTRACT FROM AUTHOR]

This paper proposes an unsupervised model to inspect various detects in fabric images with diverse textures. A fabric image with defects is usually composed of a relatively consistent background texture and some sparse defects, which can be represented as a low-rank matrix plus a sparse matrix in a certain feature space. The process is formulated as a least squares regression based subspace segmentation model, which is convex, smooth and can be solved efficiently. A simple and effective prior is also learnt from local texture features of the image itself. Instead of considering only the feature space' s global structure, the local prior is incorporated with it seamlessly by the proposed subspace segmentation model to guide and improve the segmentation. Experiments on a variety of fabric images demonstrate the effectiveness and robustness of the proposed method. Compared with existing methods, our method is more robust and locates various defects more precisely. [ABSTRACT FROM AUTHOR]