Search

Image inpainting is an effective method to repair damaged image. In this paper, we mainly studied some typical image inpainting models and analyzed these corresponding repair qualities. Firstly, we studied three typical algorithms based on PDE (Partial Differential Equation) model to repair images whose damaged areas are relative small. And then we studied the image inpainting algorithm based on texture synthesis. This kind of inpainting algorithm is suitable for image with large damaged area. Finally, we studied Criminisi inpainting algorithm based on image segmentation in detail, on which we proposed an improved priority formula image repair algorithm, the simulation results indicate that the improved algorithm of this paper showed better performance in repair quality from both subjective and objective aspects. [ABSTRACT FROM AUTHOR]

Image segmentation is an important part of the standard digital rock physics (DRP) workflows. In this paper, we present ground-truthing of digital rock images using texture analysis. We propose a deep learning–based approach for automated segmentation which is validated using the extracted ground-truth. To generate the ground-truth, we utilize the a priori knowledge of minerals and pores. We perform texture based iterative intensity thresholding to calculate the porosity and mineral composition. The ground-truth is generated for the berea sandstone image dataset and the grosmont carbonate image dataset. Results obtained from the experiments conform to the porosity and composition ranges provided in the literature. For the purpose of automated segmentation, we use a SegNet deep network which performs pixel-wise segmentation of digital rock images into pores and minerals. We train and test the SegNet using 1024 images of berea sandstone dataset ground-truthed using iterative intensity thresholding. We utilize a split of 90% and 10% for training and testing, respectively. Experimental outcomes show that the SegNet-based segmentation results for the minerals such as clay, ankerite, and zircon are better than the existing methods. [ABSTRACT FROM AUTHOR]

The paper proposes an interactive algorithm for a three-dimensional (3D) surface that can substantially improve its cracking detection performance by adjustments based on the observer's feedback. Since the correct response to the observer's feedback is critical to the performance of an interactive algorithm, the paper presents a series of novel methodologies to accomplish the interaction between the detection system and the observer with a high level of success. A computer program is developed to establish the interactive detection system and implement two levels of detection. The bottom level is automated and can be used to find the majority of cracking. The top level is assisted by the users and can be applied for semi-automated refinement. In particular, the top level is designated to find missed cracks or delete noises within user-defined regions. The techniques of precision recall and confusion matrix are used to determine effectiveness of the developed system of algorithms. The results from the case study on a highly cracked pavement segment indicate that the automated level of the proposed interactive system can achieve high detection accuracy with appropriate training, and the assisted level can retrieve nearly all cracks missed by the automated level and delete almost all noises from the processing using the automated level. [ABSTRACT FROM AUTHOR]

Medical image segmentation is fundamental and essential for the analysis of medical images. Although prevalent success has been achieved by convolutional neural networks (CNN), challenges are encountered in the domain of medical image analysis by two aspects: 1) lack of discriminative features to handle similar textures of distinct structures and 2) lack of selective features for potential blurred boundaries in medical images. In this paper, we extend the concept of contrastive learning (CL) to the segmentation task to learn more discriminative representation. Specifically, we propose a novel patch-dragsaw contrastive regularization (PDCR) to perform patch-level tugging and repulsing. In addition, a new structure, namely uncertainty-aware feature re- weighting block (UAFR), is designed to address the potential high uncertainty regions in the feature maps and serves as a better feature re- weighting. Our proposed method achieves state-of-the-art results across 8 public datasets from 6 domains. Besides, the method also demonstrates robustness in the limited-data scenario. The code is publicly available at https://github.com/lzh19961031/PDCR_UAFR-MIShttps://github.com/lzh19961031/PDCR_UAFR-MIS. [ABSTRACT FROM AUTHOR]

The study of phenomena segmentation in natural scenes has attracted growing attention and is a popular research topic. While there are many studies detailing algorithms for motion segmentation in dynamic scenes, an important question arising from these studies is how to combine these algorithms. How can the label correspondence problem be resolved? Answering this question is difficult, because there are no labeled training data available in clustering to guide the search. Also, different algorithms produce incompatible data labels resulting in intractable correspondence problems. This paper presents a new consensus model for motion segmentation in dynamic scenes, which aims to combine several unsupervised methods to achieve a more reliable and accurate result. The advantage of our method is that it is intuitively appealing. Numerical experiments on various phenomena are conducted. The performance of the proposed model is compared with the best state-of-the-art motion segmentation methods recently proposed in the literature, demonstrating the robustness and accuracy of our method. [ABSTRACT FROM AUTHOR]

In order to construct 3D meshes from a single image quickly and intuitively, this paper presents a 3D reconstruction method based on control point grid. The key idea is to calculate the 2D control point grid of the target area and elevate each control point according to a parameterized 3D growing rule proposed from prior knowledge. First, the contour of the target object is divided into a major component and side components and the skeleton of each component is extracted. 2D control point grid is calculated combining the curvature and geometric feature of the contour and lifted into 3D space with corresponding height defined by parameter mapping. Finally, a complete 3D model is obtained after component combination and texturing. Experimental results show that this method can reasonably and efficiently recover the 3D shape of the target object while maintaining fine curvature and geometric features. [ABSTRACT FROM AUTHOR]

This paper proposes a method of effectively segmenting text areas that exist in images by using the texture features of various types of input images obtained in social multimedia networks with an artificial neural network. The proposed text segmentation method consists of four main steps: a step for extracting candidate text areas, a step for localizing the text areas, a step for separating the text from the background, and a step for verifying the candidate text areas. In the candidate text area extraction step, candidate blocks that have any text areas are segmented in an input image on the basis of the texture features of the candidate blocks. In the text area localization step, only strings are extracted from the candidate text blocks. In the text and background separation step, the text areas are separated from the background area in the localized text blocks. In the candidate text area verification step, an artificial neural network is used to verify whether the extracted text blocks include actual text areas and exclude non-text areas. In the experimental results, the proposed method was applied to various types of news and non-news images, and it was found that the proposed method extracted text regions more accurately than existing methods. [ABSTRACT FROM AUTHOR]

Designing a robust image local descriptor for the purpose of image segmentation, analysis, recognition and classification has been an active area of research to date. In this paper, a robust and computationally efficient image local descriptor named 'COLOR CHILD' has been proposed. COLOR CHILD addresses the weaknesses of Weber Local Descriptor (WLD) by considering Laplacian of Gaussian (LoG) for its differential excitation component and Tiansi fractional derivative-based filter for its orientation component. For any given image, these two components are then used to construct a concatenated histogram and with the addition of color moments up to third order the capabilities of the proposed descriptor COLOR CHILD has been extended to handle textures in color space. COLOR CHILD is shown to outperform all of the known state-of-the-art image local descriptors of parametric and non-parametric types on a variety of benchmark texture databases such as KTH-TIPS2-a, KTH-TIPS2-b, and CUReT under varying degrees of noise while performing texture classification task. Further, the response profile of the COLOR CHILD in terms of Wasserstein distance measures (obtained by sliding a query patch across the image to be segmented) is found to be better suited as initial image for active contour-based image and texture segmentation algorithms. The efficacy of the COLOR CHILD for segmentation task is amply demonstrated on synthetic color images under varying degrees of noise and on real-world texture images. [ABSTRACT FROM AUTHOR]

Aiming at the problem of digital inheritance and innovation of batik fabric patterns, a method for extracting batik fabric pattern and element was proposed. First, performing morphological preprocessing on the obtained digital image of batik fabric, including morphological gradient, reconstruction and local maximum image acquisition and adjustment, not only effectively remove the texture and noise in the image, but also get a binary image that can clearly reflect the overall characteristics of the pattern and elements. Then, for the complete elements in the image, according to the labeled number, the element is reserved, and other elements are set as the background to extract each element in the image, and generate an independent elements image. Finally, the canny algorithm was used to extract the overall contour of the batik fabric pattern and elements to obtain pattern contour and elements contour that can be read and edited independently. Experimental results for different batik fabric images and image segmentation methods proved the effectiveness of the method. [ABSTRACT FROM AUTHOR]

Style transfer is a process of migrating a style from a given image to the content of another, synthesizing a new image, which is an artistic mixture of the two. Recent work on this problem adopting convolutional neural-networks (CNN) ignited a renewed interest in this field, due to the very impressive results obtained. There exists an alternative path toward handling the style transfer task, via the generalization of texture synthesis algorithms. This approach has been proposed over the years, but its results are typically less impressive compared with the CNN ones. In this paper, we propose a novel style transfer algorithm that extends the texture synthesis work of Kwatra et al. (2005), while aiming to get stylized images that are closer in quality to the CNN ones. We modify Kwatra’s algorithm in several key ways in order to achieve the desired transfer, with emphasis on a consistent way for keeping the content intact in selected regions, while producing hallucinated and rich style in others. The results obtained are visually pleasing and diverse, shown to be competitive with the recent CNN style transfer algorithms. The proposed algorithm is fast and flexible, being able to process any pair of content + style images. [ABSTRACT FROM PUBLISHER]

Texture segmentation is a very important subject in the fields of computer vision. In order to segment the textures, active contour model based on nonlocal means method and tikhonov regularization is proposed. In detail, a new nonlocal tikhonov regularization smoothness term is added. The nonlocal operator is based on the image slice similarity. So better segmentation accuracy can be achieved for the images which contain special texture features. The good matter of our method is not only nonlocal operator added but also the original tikhonov regularization smoothness item based on the pixel values retained. The nonlocal operator is time consuming, while the reserved smoothness term can save time to some extent. The traditional active contour model can only be used to segment the conventional images. The nonlocal active contour model can dispose the textures well. What's more, in order to improve the computation efficiency, this paper designs the Split-Bregman algorithm. At last, our performance is demonstrated by segmenting many real texture images. [ABSTRACT FROM AUTHOR]

Floods are natural disasters which cause the most economic damage at the global level. Therefore, flood monitoring and damage estimation are very important for the population, authorities and insurance companies. The paper proposes an original solution, based on a hybrid network and complex image processing, to this problem. As first novelty, a multilevel system, with two components, terrestrial and aerial, was proposed and designed by the authors as support for image acquisition from a delimited region. The terrestrial component contains a Ground Control Station, as a coordinator at distance, which communicates via the internet with more Ground Data Terminals, as a fixed nodes network for data acquisition and communication. The aerial component contains mobile nodes—fixed wing type UAVs. In order to evaluate flood damage, two tasks must be accomplished by the network: area coverage and image processing. The second novelty of the paper consists of texture analysis in a deep neural network, taking into account new criteria for feature selection and patch classification. Color and spatial information extracted from chromatic co-occurrence matrix and mass fractal dimension were used as well. Finally, the experimental results in a real mission demonstrate the validity of the proposed methodologies and the performances of the algorithms. [ABSTRACT FROM AUTHOR]

In computer vision, training a model that performs classification effectively is highly dependent on the extracted features, and the number of training instances. Conventionally, feature detection and extraction are performed by a domain expert who, in many cases, is expensive to employ and hard to find. Therefore, image descriptors have emerged to automate these tasks. However, designing an image descriptor still requires domain-expert intervention. Moreover, the majority of machine learning algorithms require a large number of training examples to perform well. However, labeled data is not always available or easy to acquire, and dealing with a large dataset can dramatically slow down the training process. In this paper, we propose a novel genetic programming-based method that automatically synthesises a descriptor using only two training instances per class. The proposed method combines arithmetic operators to evolve a model that takes an image and generates a feature vector. The performance of the proposed method is assessed using six datasets for texture classification with different degrees of rotation and is compared with seven domain-expert designed descriptors. The results show that the proposed method is robust to rotation and has significantly outperformed, or achieved a comparable performance to, the baseline methods. [ABSTRACT FROM PUBLISHER]

The proper analysis of biological microscopy images is an important and complex task. Therefore, it requires verification of all steps involved in the process, including image segmentation and tracking algorithms. It is generally better to verify algorithms with computer-generated ground truth datasets, which, compared to manually annotated data, nowadays have reached high quality and can be produced in large quantities even for 3D time-lapse image sequences. Here, we propose a novel framework, called MitoGen, which is capable of generating ground truth datasets with fully 3D time-lapse sequences of synthetic fluorescence-stained cell populations. MitoGen shows biologically justified cell motility, shape and texture changes as well as cell divisions. Standard fluorescence microscopy phenomena such as photobleaching, blur with real point spread function (PSF), and several types of noise, are simulated to obtain realistic images. The MitoGen framework is scalable in both space and time. MitoGen generates visually plausible data that shows good agreement with real data in terms of image descriptors and mean square displacement (MSD) trajectory analysis. Additionally, it is also shown in this paper that four publicly available segmentation and tracking algorithms exhibit similar performance on both real and MitoGen-generated data. The implementation of MitoGen is freely available. [ABSTRACT FROM PUBLISHER]

Point-based matching methods usually hold limitation in dealing with low texture scenes. In this paper, a robust affine-invariant lines matching method is proposed. The method commences with line segments extraction. All the extracted line segments are grouped into salient lines and general lines. Accordingly, the matching procedure includes salient lines matching and general lines matching. In salient lines matching, affine invariants are calculated and the matched salient line correspondences are the basis of the general lines matching. Each general line is clustered into a matched salient line according to a certain rule. Taking each salient line as the root, together with all the general lines clustered to it, a control network is constructed. Finally, the general lines matching procedure is performed between the two subnetworks whose roots are correspondences. Experimental results show that our proposed method can successfully process local distortion and improve the matching performance in low texture areas. [ABSTRACT FROM AUTHOR]

In this paper, a framework for multiscale and multifeature normalized cut (MMNCut) segmentation is proposed for high spatial resolution (HSR) remote sensing images. Normalized cuts (NCuts), as a widely used segmentation method for natural images, can obtain a globally optimized segmentation result corresponding to the optimized partitions of a graph. However, it is difficult to apply the traditional NCuts directly to HSR images because of the huge computational complexity and the diversity of the characteristics of the land covers. In order to solve these problems, the proposed MMNCuts builds a multiscale graph based on superpixels, which can provide powerful grouping cues to guide the segmentation. Generated by different algorithms with varying parameters, superpixels can capture diverse and multiscale visual patterns of HSR images. In addition, the newly constructed graph integrates the multiscale information by considering various connection relationships. Meanwhile, the successful integration of the multifeature cues, including the spectral information, texture information, and structure information, from a large number of superpixels, helps to enhance the expression ability of the graph. Computationally, this leads to a much more efficient algorithm than the traditional NCuts, and in effect, the proposed method achieves a significantly better performance than the traditional approaches. The experimental results with three HSR image data sets demonstrate that the proposed MMNCut algorithm shows a competitive performance in both qualitative and quantitative evaluations when compared with the other state-of-the-art segmentation algorithms for HSR images. [ABSTRACT FROM AUTHOR]

It is evident that crowd counting is one of bottlenecks for crowd-related computer vision theory and applications such as surveillance. Since accuracy of estimating crowd size dominantly depends on the performance of motion detection of pedestrians, this paper attacks the challenging problem mainly by proposing a motion segmentation method based on flow field texture representation. Firstly, the motion crowd and background are represented as different texture images by employing line integral convolution. Then information entropy is introduced to quantify the textures as different values so that the texture images can be segmented; further an optimal threshold is obtained via Otsu method to segment the binarization entropy image. Finally, the area of motion foreground pixels is calculated for each image in a crowd motion video. The size of the crowd is estimated by least squares fitting using abundant datum of foreground pixels' area and the number of individuals in a crowd. Experimental results demonstrate that the proposed crowd counting method outperforms background subtraction, Gaussian mixture model and optical flow-based methods in terms of mean absolute error and mean relative error. [ABSTRACT FROM AUTHOR]

When dealing with lines in regions with sparse texture, such as satellite's brackets, some existing line matching methods do not work well due to the incorrect location of line endpoints and line fragments. In this paper, we study how to automatically match low-textured lines. The designed feature only uses their neighborhood appearance and there are no any other prior knowledge or constraints needed. We combine point and line features to propose a novel line matching method. It includes the following three main steps. First, line extraction based on pixel gradient is adopted and we design a mergence strategy to ensure continuity. Then, line-point invariant and center-symmetric local binary pattern descriptor are combined together to represent lines. Last, two corresponding criterions are designed to measure the similarities between each pair images. Extensive experiments on real and synthetic images show that our proposed method exceeds the reference methods in performance under scale, illumination, and dynamic cases. [ABSTRACT FROM AUTHOR]

In this paper, texture probabilistic grammar is defined for the first time. We have developed an algorithm to obtain the 3D information in a 2D scene by training the texture probabilistic grammar from the prebuilt model library. The well-trained texture probabilistic grammar could also be applied to 3D reconstruction. Our detailed process contains: dividing the 2D scene into texture fragments; assigning the most suitable 3D object label to the 2D texture fragments; using our texture probabilistic grammar to predict 3D information of the texture fragments in 2D scene image; constructing the 3D model of the original 2D scene image. Through experiments, it is proved that the algorithm has a better effect on reconstruction of indoor scenes and building structures, and the algorithm is superior to the traditional reconstruction method based on point clouds. Different datasets and reconstructed objects are tested, which verifies the robustness of the algorithm. As a result, our algorithm is able to deal with the large numbers of scenes with similar semantics and it is also fast enough to deal with the online 3D reconstruction. [ABSTRACT FROM AUTHOR]

High resolution remote-sensing images provide abundant color, shape structure and texture information. However, region-based segmentations do not allow to fully exploit the richness of this kind of images. Despite the enormous progress in the analysis of remote sensing imagery over the past three decades, there is a lack of guidance on how to select an image segmentation algorithm suitable for the image type and size. In accordance with the characteristics of color high-resolution remote sensing images, we put forward an improved region filter remote-sensing color-image segmentation algorithm based on traditional JSEG segmentation. In order to well describe the color homogeneity in region, the local homogeneity matrix can be adopted to correct the local value in traditional JSEG segmentation algorithm so as to accurately reflect the boundary region and enhance the accuracy of image segmentation. Simulation experiment results demonstrate that our proposed algorithm can efficiently overcome the inaccurate segmentation of boundary region. In addition, compared with the traditional filter algorithm, our proposed algorithm can extract weak edge more accurately so as to achieve the better segmentation result in high resolution remote-sensing image segmentation. [ABSTRACT FROM AUTHOR]

This paper presents a method for increasing spatial resolution of a depth map using its corresponding high-resolution (HR) color image as a guide. Most of the previous methods rely on the assumption that depth discontinuities are highly correlated with color boundaries, leading to artifacts in the regions where the assumption is broken. To prevent scene texture from being erroneously transferred to reconstructed scene surfaces, we propose a framework for dividing the color image into different regions and applying different methods tailored to each region type. For the region classification, we first segment the low-resolution (LR) depth map into regions of smooth surfaces, and then use them to guide the segmentation of the color image. Using the consensus of multiple image segmentations obtained by different super-pixel generation methods, the color image is divided into continuous and discontinuous regions: in the continuous regions, their HR depth values are interpolated from LR depth samples without exploiting the color information. In the discontinuous regions, their HR depth values are estimated by sequentially applying more complicated depth-histogram-based methods. Through experiments, we show that each step of our method improves depth map upsampling both quantitatively and qualitatively. We also show that our method can be extended to handle real data with occluded regions caused by the displacement between color and depth sensors. [ABSTRACT FROM PUBLISHER]

This paper presents a novel combined energy functional based on edge and region information for active contour model, which can be applied to segment textured images containing low contrast and high illumination variations. In the proposed method, the edge features are calculated based on the phase-based approaches derived from the monogenic signal, which are robust to illumination variations in the image. These feature values are used in an edge energy functional to assist the active contour evolving towards the true object boundaries. To extract the region features, at first, we compute the normalized accumulated short-term autocorrelation (NASTA) values for the image, which suppress background clutter and enhance dissimilarities between objects and background. Next, a local cumulative distribution function (LCDF) of NASTA is calculated for every pixel in a local window around it and is used as a region feature for that pixel. Then, the obtained features are employed to define a new localized region-based energy functional that can correctly segment regions with same intensity mean and variance. The proposed edge and region energy terms are integrated and a regularization term is added to them to form our combined active contour. Experimental results indicate remarkable advantages of proposed method comparing to existing combination models. [ABSTRACT FROM AUTHOR]

The automatic detection, segmentation, localization, and evaluation of the optic disc, macula, exudates, and hemorrhages are very important for diagnosing retinal diseases. One of the difficulties in detecting such regions of interest (RoIs) with computer vision is their symmetries, e.g., between the optic disc and exudates and also between exudates and hemorrhages. This paper proposes an original, intelligent, and high-performing image processing system for the simultaneous detection and segmentation of retinal RoIs. The basic principles of the method are image decomposition in small boxes and local texture analysis. The processing flow contains three phases: preprocessing, learning, and operating. As a first novelty, we propose proper feature selection based on statistical analysis in confusion matrices for different feature types (extracted from a co-occurrence matrix, fractal type, and local binary patterns). Mainly, the selected features are chosen to differentiate between similar RoIs. The second novelty consists of local classifier fusion. To this end, the local classifiers associated with features are grouped in global classifiers corresponding to the RoIs. The local classifiers are based on minimum distances to the representatives of classes and the global classifiers are based on confidence intervals, weights, and a voting scheme. A deep convolutional neural network, based on supervised learning, for blood vessel segmentation is proposed in order to improve the RoI detection performance. Finally, the experimental results on real images from different databases demonstrate the rightness of our methodologies and algorithms. [ABSTRACT FROM AUTHOR]

The quality of olive fruit and its virgin olive oil is a main concern for consumers and fruit industrial companies. The effectiveness and fast detection of olive's skin defects is the most decisive factor in determining its quality. It is necessary to design and implement image processing tools for segmentation and correct classification of the different fresh incoming olive batches. In this paper, we propose a new automatic image segmentation algorithm, based on discrete wavelets transform. The aim of the segmentation algorithm is to discriminate between olives and the background with the challenge of irregular and dispersive lesion borders, low contrast, artifacts in the olive fruit and variety of colors within the interest region. The second part of our work proposes a scheme for olive fruit classification. The classifier first identifies the olive fruit color and then, based upon discrete wavelets transform and Tamura statistical texture features, the healthy olive fruit is distinguished from the damaged one. The new texture feature vector is, then, compared with the robust Local Binary Pattern feature vector. The simplicity of our segmentation and classification algorithms makes them appropriate for designing a productive and profitable computer vision machine. [ABSTRACT FROM AUTHOR]

Crude oil spills have negative consequences on the economy, environment, health and society in which they occur, and the severity of the consequences depends on how quickly these spills are detected once they begin. Several methods have been employed for spill detection, including real time remote surveillance by flying aircrafts with surveillance teams. Other methods employ various sensors, including visible sensors. This paper presents an algorithm to automatically detect the presence of crude oil spills in images acquired using visible light sensors. Images of crude oil spills used in the development of the algorithm were obtained from the Shell Petroleum Development Company (SPDC) Nigeria website The major steps of the detection algorithm are image preprocessing, crude oil color segmentation, sky elimination segmentation, Region of Interest (ROI) extraction, ROI texture feature extraction, and ROI texture feature analysis and classification. The algorithm was developed using 25 sample images containing crude oil spills and demonstrated a sensitivity of 92% and an FPI of 1.43. The algorithm was further tested on a set of 56 case images and demonstrated a sensitivity of 82% and an FPI of 0.66. This algorithm can be incorporated into spill detection systems that utilize visible sensors for early detection of crude oil spills. [ABSTRACT FROM AUTHOR]

Infrared and visible imaging play crucial roles in non-destructive testing, where accurate defect segmentation and detection are paramount. However, the scarcity of annotated training data or the limited number of data availability often poses a challenge. To address this, we propose an innovative framework tailored to the domain of infrared and visible imaging, integrating segmentation and detection tasks. The proposed approach eliminates the dependency on annotated defect data during training, enabling models to adapt to real-world scenarios with limited annotations. By utilizing super-pixel segmentation and texture analysis, the proposed method enhances the accuracy of defect detection. Concrete structures, globally subjected to aging and degradation, demand constant monitoring for structural health. Traditional manual crack detection methods are labor-intensive, necessitating automated systems. The proposed approach combines deep learning-based super-pixel segmentation with texture analysis, offering a solution for limited-defect-data situations. Utilizing convolutional neural networks (CNNs) for super-pixel segmentation and texture features for defect analysis, the proposed methodology improves the efficiency and accuracy of crack detection, especially in scenarios with limited labeled data or a limited number of data available. Evaluation on public benchmark datasets have validated the effectiveness of the proposed approach in detecting cracks in concrete structures. [ABSTRACT FROM AUTHOR]

This paper presents a method for the combination of different feature cues in a level set based moving object segmentation framework. To distinguish object from background, motion detection is firstly adopted to locate object position and obtain coarse shape prior. Moreover, the color and texture feature descriptors that represent object contour are designed in this dissertation. Then the finer segmentation solution based on the color and texture difference between the object and background is proposed, which avoids the invalid feature components to hamper segmentation and improves the accuracy. Extensive experiments have been carried out on surveillance video sequences to validate the proposed method. [ABSTRACT FROM AUTHOR]

Spectral information alone is often not sufficient to distinguish certain terrain classes such as permanent crops like orchards, vineyards, and olive groves from other types of vegetation. However, instances of these classes possess distinctive spatial structures that can be observable in detail in very high spatial resolution images. This paper proposes a novel unsupervised algorithm for the detection and segmentation of orchards. The detection step uses a texture model that is based on the idea that textures are made up of primitives (trees) appearing in a near-regular repetitive arrangement (planting patterns). The algorithm starts with the enhancement of potential tree locations by using multi-granularity isotropic filters. Then, the regularity of the planting patterns is quantified using projection profiles of the filter responses at multiple orientations. The result is a regularity score at each pixel for each granularity and orientation. Finally, the segmentation step iteratively merges neighboring pixels and regions belonging to similar planting patterns according to the similarities of their regularity scores and obtains the boundaries of individual orchards along with estimates of their granularities and orientations. Extensive experiments using Ikonos and QuickBird imagery as well as images taken from Google Earth show that the proposed algorithm provides good localization of the target objects even when no sharp boundaries exist in the image data. [ABSTRACT FROM PUBLISHER]

This paper addresses statistical-based texture modeling using wavelets. We propose a new approach to represent the marginal distribution of the wavelet coefficients using finite mixtures of generalized Gaussian (MoGG) distributions. The MoGG captures a wide range of histogram shapes, which provides better description and discrimination of texture than using single probability density functions (pdf's), as proposed by recent state-of-the-art approaches. Moreover, we propose a model similarity measure based on Kullback–Leibler divergence (KLD) approximation using Monte Carlo sampling methods. Through experiments on two popular texture data sets, we show that our approach yields significant performance improvements for texture discrimination and retrieval, as compared with recent methods of statistical-based wavelet modeling. [ABSTRACT FROM AUTHOR]

In this paper, we present a caricature generation technique with different styles, which consists of shape exaggeration, relationship exaggeration and style transfer algorithm of caricature. Rather than transferring texture from one image to another globally, we introduce an interactive tool for local texture transfer. A brush is used to draw strokes on the source and target images to indicate corresponding regions in that the segmentation algorithm method is considered to be not ideal in this case. Multiple local texture transfer method is presented to transfer the texture from the source region to the destination region through patch-based texture synthesis. Experimental results demonstrate that the proposed algorithm is easy and effective in generating different artistic effects in caricature. [ABSTRACT FROM AUTHOR]

Many image editing applications rely on the analysis of image patches. In this paper, we present a method to analyze patches by embedding them to a vector space, in which the Euclidean distance reflects patch similarity. Inspired by Word2Vec, we term our approach Patch2Vec. However, there is a significant difference between words and patches. Words have a fairly small and well defined dictionary. Image patches, on the other hand, have no such dictionary and the number of different patch types is not well defined. The problem is aggravated by the fact that each patch might contain several objects and textures. Moreover, Patch2Vec should be universal because it must be able to map never-seen-before texture to the vector space. The mapping is learned by analyzing the distribution of all natural patches. We use Convolutional Neural Networks (CNN) to learn Patch2Vec. In particular, we train a CNN on labeled images with a triplet-loss objective function. The trained network encodes a given patch to a 128D vector. Patch2Vec is evaluated visually, qualitatively, and quantitatively. We then use several variants of an interactive single-click image segmentation algorithm to demonstrate the power of our method. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel target contour tracking method under sophisticated background using the multiple cues-based active contour model. To locate the target position, a contour-based mean-shift tracker is designed which combines both color and texture information. To reduce the adverse impact of sophisticated background and also accelerate the curve motion, we propose a two-layer-based target appearance model that combines both discriminative pre-learned-based global layer and voting-based local layer. The proposed appearance model is able to extract rough target region from the complex background, which provides important target region information for our active contour model. We subsequently introduce a dynamical shape model to provide prior target shape information for more stable segmentation. To obtain accurate target boundaries, we design a new multiple cues-based active contour model which integrates with target edge, discriminative region, and shape information. The experimental results on 30 video sequences demonstrate that the proposed method outperforms other competitive contour tracking methods under various tracking environment. [ABSTRACT FROM AUTHOR]

In a recent paper, a method called “texture characteristic based morphological component analysis” (TC-MCA) has been proposed to enhance the performances of texture-based image segmentation algorithms: (1) TC-MCA separates texture into multiple pairs of components each representing a different visual characteristic of the texture; (2) then the TC-MCA algorithm manipulates each component and recombines them to produce the enhanced image where textures are more different, so that the texture-based segmentation is improved. This paper proposes a novel method outperforming TC-MCA by: (1) applying dictionaries based on dual-tree complex wavelet transform (DTCWT) to decompose the image into components representing different visual characteristics of texture, and (2) manipulating the dual-tree complex wavelet coefficients of the texture components to enhance each texture component’s own property and producing an texture-difference-enhanced image by recombining the enhanced components. The wavelet-based texture characteristic morphological component analysis (WT-TC-MCA) is applied as the preprocessing step to some state-of-the-art texture-based segmentation algorithms and compared with other texture enhancing methods, including the TC-MCA, with respect to the accuracy, precision-recall curves of the segmentation results. Experiments demonstrate that our method produces better textural difference enhancement effects and improves texture-based segmentation more than the comparators. [ABSTRACT FROM AUTHOR]

In this paper a non-parametric model based on Wasserstein CNN is proposed for color correction. It is suitable for large-scale remote sensing image preprocessing from multiple sources under various viewing conditions, including illumination variances, atmosphere disturbances, and sensor and aspect angles. Color correction aims to alter the color palette of an input image to a standard reference which does not suffer from the mentioned disturbances. Most of current methods highly depend on the similarity between the inputs and the references, with respect to both the contents and the conditions, such as illumination and atmosphere condition. Segmentation is usually necessary to alleviate the color leakage effect on the edges. Different from the previous studies, the proposed method matches the color distribution of the input dataset with the references in a probabilistic optimal transportation framework. Multi-scale features are extracted from the intermediate layers of the lightweight CNN model and are utilized to infer the undisturbed distribution. The Wasserstein distance is utilized to calculate the cost function to measure the discrepancy between two color distributions. The advantage of the method is that no registration or segmentation processes are needed, benefiting from the local texture processing potential of the CNN models. Experimental results demonstrate that the proposed method is effective when the input and reference images are of different sources, resolutions, and under different illumination and atmosphere conditions. [ABSTRACT FROM AUTHOR]

In this paper, we propose a generalization of the level set segmentation approach by supplying a novel method for adaptive estimation of active contour parameters. The presented segmentation method is fully automatic once the lesion has been detected. First, the location of the level set contour relative to the lesion is estimated using a convolutional neural network (CNN). The CNN has two convolutional layers for feature extraction, which lead into dense layers for classification. Second, the output CNN probabilities are then used to adaptively calculate the parameters of the active contour functional during the segmentation process. Finally, the adaptive window size surrounding each contour point is re-estimated by an iterative process that considers lesion size and spatial texture. We demonstrate the capabilities of our method on a dataset of 164 MRI and 112 CT images of liver lesions that includes low contrast and heterogeneous lesions as well as noisy images. To illustrate the strength of our method, we evaluated it against state of the art CNN-based and active contour techniques. For all cases, our method, as assessed by Dice similarity coefficients, performed significantly better than currently available methods. An average Dice improvement of 0.27 was found across the entire dataset over all comparisons. We also analyzed two challenging subsets of lesions and obtained a significant Dice improvement of 0.24 with our method (p <0.001, Wilcoxon). [ABSTRACT FROM AUTHOR]

Nowadays, image processing is an interesting research area due to the growth of the communication technologies. Matching problem, which consists of localizing one texture in an image, that contains several textures is one of the fundamental problem of image processing and pattern recognition. In this paper, a new feature extraction method and texture segmentation system are proposed. The proposed method (RINBP) is robust against rotation and improves the ability of extracting the local information. The segmentation architecture follows several steps. First, fixing a converging point α. After that, a Main analysis Window (MW) starting from α to the bottom left corner of the image is determined. Then, several possible windows are extracted and the feature extraction method is applied on each window. Finally, a similarity measure is calculated in order to decide if this window is pertinent or not. This process is stopped until the size of the MW reaches a minimum size. Each pertinent window increases the relevance of the desired texture in the output image. Finally, an image of relevance is obtained by considering the most relevant area. For the experiments, textured images generated from Brodatz album database are used. The experiments have shown the superiority of our method compared to other existing methods. The obtained results have illustrated the robustness and the efficiency of the proposed segmentation method based on the relevance of the analysis windows. [ABSTRACT FROM AUTHOR]

This paper presents a comparison of color spaces for material classification. The study includes three device-independent (CIELAB, CIELUV, and CIE XYZ) and seven device-dependent spaces (RGB, HSV, YIQ, YUV, YCbCr, Ohta's I1 l2I3, and RG-YeB-WhBI). The pros and cons of the different spaces and the procedures for converting color data among them are discussed in detail. An experiment based on 12 different image data sets was carried out to comparatively evaluate the performance of each space for material classification purposes. The results showed that CIELAB markedly outperformed the other spaces followed by HSV and CIELUV. Conversely, CIE XYZ came out as the worst performing space. Interestingly, no significant difference emerged among the performance of the other device-dependent spaces. [ABSTRACT FROM AUTHOR]

Textural information is extracted via Haralick's features from each partition to conform a feature vector, and a joint color-texture representation is obtained by merging the color code and a normalized texture descriptor. Texture and color are two types of visual stimuli that determine, to a great extent, the appearance of objects, materials, and scenes. They applied several texture models such as co-occurrences, first-order features, run-length matrices, gray-tone difference matrices, and local binary patterns to transform DIR images into feature maps. Smeraldi et al. [[2]] proposed a novel framework for color texture analysis based on partial orderings. [Extracted from the article]

This paper proposes an automated analysis system for Tatami embroidery fabric images that automates color analysis, pattern shape analysis and texture analysis. Firstly, the RGB (red, green and blue) image of embroidery fabric is obtained by a color scanner. In color analysis, the wavelet transforms and median filter are used for RGB image preprocessing, and then the Fuzzy C-Means (FCM) clustering method is used for the binary region splitting method, the color features of statistical values of colors and number of colors can be obtained. In the pattern shape analysis, the individual pattern components are segmented by the separated colors, and the shape features of pattern components are obtained by moment invariants. Finally, in the texture analysis of Tatami embroidery fabrics, the gray image of the weave block is segmented from the pattern component region, after the entropy filter, the parallel division lines are segmented by a threshold value, and then the angle and spacing between Tatami embroidery parallel division lines are obtained by Hough transform to represent texture features. The experimental results show that this method can implement Tatami embroidery fabric color, shape and texture analyses automatically. [ABSTRACT FROM AUTHOR]

Vanishing-point detection is an important component for the visual navigation system of an autonomous mobile robot. In this paper, we present a novel line space voting method for fast vanishing-point detection. First, the line segments are detected from the road image by the line segment detector (LSD) method according to the pixel's gradient and texture orientation computed by the Sobel operator. Then, the vanishing-point of the road is voted on by considering the points of the lines and their neighborhood spaces with weighting methods. Our algorithm is simple, fast, and easy to implement with high accuracy. It has been experimentally tested with over hundreds of structured and unstructured road images. The experimental results indicate that the proposed method is effective and can meet the real-time requirements of navigation for autonomous mobile robots and unmanned ground vehicles. [ABSTRACT FROM AUTHOR]

Visual textures have played a key role in image understanding because they convey important semantics of images, and because texture representations that pool local image descriptors in an orderless manner have had a tremendous impact in diverse applications. In this paper we make several contributions to texture understanding. First, instead of focusing on texture instance and material category recognition, we propose a human-interpretable vocabulary of texture attributes to describe common texture patterns, complemented by a new describable texture dataset for benchmarking. Second, we look at the problem of recognizing materials and texture attributes in realistic imaging conditions, including when textures appear in clutter, developing corresponding benchmarks on top of the recently proposed OpenSurfaces dataset. Third, we revisit classic texture represenations, including bag-of-visual-words and the Fisher vectors, in the context of deep learning and show that these have excellent efficiency and generalization properties if the convolutional layers of a deep model are used as filter banks. We obtain in this manner state-of-the-art performance in numerous datasets well beyond textures, an efficient method to apply deep features to image regions, as well as benefit in transferring features from one domain to another. [ABSTRACT FROM AUTHOR]

Fingerprint recognition plays an important role in many commercial applications and is used by millions of people every day, e.g. for unlocking mobile phones. Fingerprint image segmentation is typically the first processing step of most fingerprint algorithms and it divides an image into foreground, the region of interest, and background. Two types of error can occur during this step which both have a negative impact on the recognition performance: ‘true’ foreground can be labeled as background and features like minutiae can be lost, or conversely ‘true’ background can be misclassified as foreground and spurious features can be introduced. The contribution of this paper is threefold: firstly, we propose a novel factorized directional bandpass (FDB) segmentation method for texture extraction based on the directional Hilbert transform of a Butterworth bandpass (DHBB) filter interwoven with soft-thresholding. Secondly, we provide a manually marked ground truth segmentation for 10560 images as an evaluation benchmark. Thirdly, we conduct a systematic performance comparison between the FDB method and four of the most often cited fingerprint segmentation algorithms showing that the FDB segmentation method clearly outperforms these four widely used methods. The benchmark and the implementation of the FDB method are made publicly available. [ABSTRACT FROM AUTHOR]

In order to improve the performance of image segmentation, this paper presented a gray level jump segmentation algorithm, which defined the direction of the texture, simultaneously, calculated the width of ridge line, gave the distance characteristics between textures, and established the mathematical model of the texture border, accordingly presented a new texture segmentation algorithm and compared with other texture segmentation algorithms. The simulation results show that the segmentation algorithm has some advantages to texture segmentation, such as has higher segmentation precision, faster segmentation speed, stronger anti-noise capability, less lost information of target, and so on. The segmented regions hardly contain other texture regions and background region. Moreover, this paper extracted the characteristic points and characteristic parameters in various segmented regions for texture image to obtain the characteristic vector, compared the characteristic vector with the standard template vectors, and identified the type of target in a range of threshold value. Experimental results show that the proposed target recognition approach has higher recognition rate and faster recognition speed than the existing target recognition approaches. Advancements in image processing through the study of texture segmentation are not only applicable to image fields, but also are of important theoretical value to target recognition. These researches in this paper will play an important role in a theoretical reference and practical significance to the development of all target recognition departments based on image system such as the aerospace, public security, road traffic, and so on. [ABSTRACT FROM AUTHOR]

This paper presents a novel double-layer sparse representation (DLSR) approach, for improving both reconstructive and discriminative capabilities of unsupervised dictionary learning. In supervised/unsupervised discriminative dictionary learning, classical approaches usually develop a discriminative term for learning multiple sub-dictionaries, each of which corresponds to one-class training image patches. As such, the image patches for different classes can be discriminated by coefficients of sparse representation, with respect to different sub-dictionaries. However, in the unsupervised scenario, some of the training patches for learning the sub-dictionaries of different clusters are related to more than one cluster. Thus, we propose a DLSR formulation in this paper to impose the first-layer sparsity on the coefficients and the second-layer sparsity on the clusters for each training patch, embedding both the reconstructive (via the first-layer) and discriminative (via the second-layer) capabilities in the learned dictionary. To address the proposed DLSR formulation, a simple yet effective algorithm, called DLSR-OMP, is developed on the basis of the conventional OMP algorithm. Finally, the experiments verify that our approach can improve reconstruction and clustering performance of the learned dictionaries of the conventional approaches. More importantly, the experimental results on texture segmentation show that our approach outperforms other state-of-the-art discriminative dictionary learning approaches in the clustering task. [ABSTRACT FROM AUTHOR]

Real-world images usually contain vivid contents and rich textural details, which will complicate the manipulation on them. In this paper, we design a new framework based on exampled-based texture synthesis to enhance content-aware image retargeting. By detecting the textural regions in an image, the textural image content can be synthesized rather than simply distorted or cropped. This method enables the manipulation of textural & non-textural regions with different strategies since they have different natures. We propose to retarget the textural regions by example-based synthesis and non-textural regions by fast multi-operator. To achieve practical retargeting applications for general images, we develop an automatic and fast texture detection method that can detect multiple disjoint textural regions. We adjust the saliency of the image according to the features of the textural regions. To validate the proposed method, comparisons with state-of-the-art image retargeting techniques and a user study were conducted. Convincing visual results are shown to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM PUBLISHER]

Purpose: Whole-body positron emission tomography/computed tomography (PET/CT) has become a standard method of imaging patients with various disease conditions, especially cancer. Body-wide accurate quantification of disease burden in PET/CT images is important for characterizing lesions, staging disease, prognosticating patient outcome, planning treatment, and evaluating disease response to therapeutic interventions. However, body-wide anatomy recognition in PET/CT is a critical first step for accurately and automatically quantifying disease body-wide, body-region-wise, and organwise. This latter process, however, has remained a challenge due to the lower quality of the anatomic information portrayed in the CT component of this imaging modality and the paucity of anatomic details in the PET component. In this paper, the authors demonstrate the adaptation of a recently developed automatic anatomy recognition (AAR) methodology [Udupa et al., "Body-wide hierarchical fuzzy modeling, recognition, and delineation of anatomy in medical images," Med. Image Anal. 18, 752-771 (2014)] to PET/CT images. Their goal was to test what level of object localization accuracy can be achieved on PET/CT compared to that achieved on diagnostic CT images. Methods: The authors advance the AAR approach in this work in three fronts: (i) from body-regionwise treatment in the work of Udupa et al. to whole body; (ii) from the use of image intensity in optimal object recognition in the work of Udupa et al. to intensity plus object-specific texture properties, and (iii) from the intramodality model-building-recognition strategy to the intermodality approach. The whole-body approach allows consideration of relationships among objects in different body regions, which was previously not possible. Consideration of object texture allows generalizing the previous optimal threshold-based fuzzy model recognition method from intensity images to any derived fuzzy membership image, and in the process, to bring performance to the level achieved on diagnostic CT and MR images in body-region-wise approaches. The intermodality approach fosters the use of already existing fuzzy models, previously created from diagnostic CT images, on PET/CT and other derived images, thus truly separating the modality-independent object assembly anatomy from modality-specific tissue property portrayal in the image. Results: Key ways of combining the above three basic ideas lead them to 15 different strategies for recognizing objects in PET/CT images. Utilizing 50 diagnostic CT image data sets from the thoracic and abdominal body regions and 16 whole-body PET/CT image data sets, the authors compare the recognition performance among these 15 strategies on 18 objects from the thorax, abdomen, and pelvis in object localization error and size estimation error. Particularly on texture membership images, object localization is within three voxels on whole-body low-dose CT images and 2 voxels on body-region-wise low-dose images of known true locations. Surprisingly, even on direct body-region-wise PET images, localization error within 3 voxels seems possible. Conclusions: The previous body-region-wise approach can be extended to whole-body torso with similar object localization performance. Combined use of image texture and intensity property yields the best object localization accuracy. In both body-region-wise and whole-body approaches, recognition performance on low-dose CT images reaches levels previously achieved on diagnostic CT images. The best object recognition strategy varies among objects; the proposed framework however allows employing a strategy that is optimal for each object. [ABSTRACT FROM AUTHOR]

Due to complex nature of blood smear images and imitation of similar signs of other disorders makes difficult to detect leukemia. It also needs more time to diagnose and sometimes susceptible to errors. In order to solve this issues fuzzy C means cluster optimization of leukemia detection based on morphological contour segmentation is proposed in this paper. This paper introduces the new approach for leukemia detection which consist of (1) contrast enhancement to highlights the nuclei, (2) morphological contour segmentation, and (3) Fuzzy C means detection of leukemia. The contract enhancement is done by simple addition and subtraction operation to separate the nuclei. The morphological contour segmentation detects the edges of nuclei and eliminate the normal white blood cells from the microscopic blood image. Then the texture, geometry, color and statistical features of nuclei is evaluated to determines the various factors of leukemia. Finally it is trained by Fuzzy C mean clustering of single row feature vector of each cell is used to classify leukemia from white blood cells. This makes the proposed algorithm better results in accuracy and time consumption when compare to normal hematologist's visual classification. [ABSTRACT FROM AUTHOR]