Search

This paper proposes a new and improved one-dimensional chaotic system (1DL-SCS). After performance testing, it is verified to have better chaotic performance and a larger range of parameters. Based on this, a new image encryption algorithm is proposed. First, the chaotic sequences generated by the hyper-chaotic Chen system are used to perform twice circular rotations for achieving efficient global scrambling. Then we index scramble the image by row using 1DL-SCS and redistribute the pixel points by column, which further breaks the correlation between image pixels and prepares for diffusion. In the diffusion stage, the plaintext is divided into four parts for processing with the improved generalized Feistel structure, and the plaintext sequence in the round function is further divided into two parts, which greatly improves the diffusion efficiency. Through two rounds of iterative operations, a good diffusion effect can be achieved efficiently. Simulation experiment and performance analysis indicates that the algorithm has outstanding advantages such as excellent ciphertext statistical characteristics, and strong resistance to chosen plaintext attacks. [ABSTRACT FROM AUTHOR]

Although a wide variety of background subtraction methods has been proposed in recent years, none has been able to fully address multi-scale moving objects and dynamic background in real surveillance tasks. In this paper, a novel and effective background subtraction method, named regional multi-feature-frequency (RMFF), is proposed to detect multi-scale moving objects under dynamic background. Unlike many existing methods construct background model using simple multi-feature combinations, RMFF exploits the spatiotemporal cues of multi-feature as well as superpixels at each scale, thus allowing for more robust information to be exploited for background modeling. Specifically, the spatial relationship between pixels in a neighborhood and the frequencies of features over time are first exploited, enabling accurate detection of moving objects while ignoring most dynamic background changes. Then, the use of multi-scale superpixels for exploiting the structural information existing in real-world scenes further enhances robustness to multi-scale objects and environmental variations. Finally, an adaptive strategy is employed to dynamically adjust the foreground/background segmentation threshold for each region without user intervention. This adaptive threshold is defined for each region separately, and can adjust dynamically based on continuous monitoring of the background changes, thereby effectively reducing potential segmentation noise. Experiments on the 2014 version of the ChangeDetection.net dataset demonstrate that the proposed method outperforms the 12 state-of-the-art algorithms in terms of overall F-Measure and performs effectively in many complex scenes. Consequently, it is verified that the developed approach is feasible and useful for robust application in practical video surveillance. [ABSTRACT FROM AUTHOR]

This paper proposes a blind color image watermarking method based on Hadamard transform to deal with the infringement of color images in the complex network environment. First of all, the color watermark image is channeled and each pixel in the channel image is converted into an 8-bit binary code. And then, the color host image is also channeled and expanded into 4 × 4 non-overlapping pixel blocks based on the selected embedding position. Finally, Hadamard transform is put on the pixel block, and 1-bit watermark information is embedded by the coefficient pair of the first line of Hadamard coefficient matrix. When extracting watermark, the watermark can be extracted only by comparing the size relationship of the coefficient pairs without the help of the original image. In this paper, a voting system of the minority obeying the majority is designed and implemented, which actually enhances the robustness of the method. In addition, a high security encryption system is designed by combining symmetric key and public key, and the correlation between RGB color channels is considered. Simulation results show that the proposed method has better robustness, real-time performance and security compared with similar methods, and meets certain requirements in terms of invisibility and capacity. [ABSTRACT FROM AUTHOR]

The purpose of this research is to develop a highly secured non-breakable fastest cryptosystem. A significant number of image encryption plans have been proposed during the past years. By far, most such plans arrive at a high-security level; be that as it may, their moderate velocities due to their complex phenomenon make them of no utilization progressively applications. Motivated by this, we propose another proficient and quick image encryption plan subject to the trigonometric turbulent guide. In contrast with most current plans, we utilize this basic map to create just a couple of arbitrary rows and columns in the form of S-boxes. Besides, to, moreover, accelerate, we raise the handling unit from the pixel level to the line/segment level. Security of the new plan is acquired through a replacement stage organization, where we implemented around the shift of lines and segments to break the strong relation between adjoining pixels and non-repeating sequences. By then, we join the Exclusive-OR operation with modulo capacity to cover the pixel esteems and avoid any spilling of information. High-security tests and reenactment examinations have been done to display that the plan is extremely safe and particularly speedy for continuous picture preparation at 80 fps (frames per second). The present research has developed a cryptosystem based on Exclusive-OR with S-box (Substitution Box) and trigonometric chaotic map (TCM) of image matrices. High security is achieved due to the non-repeating sequence of the TCM. Earlier, the author has already presented the efficacy of the TCM combined with the S-Boxes. [ABSTRACT FROM AUTHOR]

Digital topologists are concerned with the properties of two- or three-dimensional digital images that correspond to topological properties of objects, such as connectedness and boundaries. Via bounded descriptive neighborhoods, one of the important concepts of digital topology, which has various applications in the literature, we present a study of how to recognize changes in a residential district, such as buildings constructed or demolished over time under some assumptions. Roughly speaking, our way of doing this is to calculate the corresponding pixel topologies of the subimages of the two maps divided into equal number of rectangular regions and to find the union of the symmetric differences between the elements of these topologies according to a certain threshold value. In this study, we use grayscale bird's-eye views of the same residential district taken at two different times. As the main emphasis of this study, we show that one of the application areas of digital topology, which underlies our algorithms in which pseudo and Mathematica codes are given, is geographic information systems. [ABSTRACT FROM AUTHOR]

This paper proposes PatternAttack to mitigate two major issues of Adversarial Transformation Network (ATN) including the low diversity and the low quality of adversarial examples. In order to deal with the first issue, this research proposes a stacked convolutional autoencoder based on patterns to generalize ATN. This proposed autoencoder could support different patterns such as all-pixel pattern, object boundary pattern, and class model map pattern. In order to deal with the second issue, this paper presents an algorithm to improve the quality of adversarial examples in terms of L 0 -norm and L 2 -norm. This algorithm employs adversarial pixel ranking heuristics such as JSMA and COI to prioritize adversarial pixels. To demonstrate the advantages of the proposed method, comprehensive experiments have been conducted on the MNIST dataset and the CIFAR-10 dataset. For the first issue, the proposed autoencoder generates diverse adversarial examples. For the second issue, the proposed algorithm significantly improves the quality of adversarial examples. In terms of L 0 -norm, the proposed algorithm decreases from hundreds of adversarial pixels to one adversarial pixel. In terms of L 2 -norm, the proposed algorithm reduces the average distance considerably. These results show that the proposed method can generate high-quality and diverse adversarial examples in practice. [ABSTRACT FROM AUTHOR]

The rapid development of image encryption and reversible data hiding technology provides protection of image copyright and privacy. For flexible management of encrypted images, there is a great deal of attention given to embedding information on encrypted images. In this paper, we propose a new technology that combines image encryption and data hiding. In the image encryption section, we propose an encryption technology that preserves the difference between pixels so that reversible data hiding can be effectively used in encrypted images. In addition, we cleverly designed the encryption so that overflow issues when embedding information does not occur in encrypted images. In the embedding information section, we adopt the histogram shifting method to conceal the secret message. We propose a technology that combines encryption and data hiding; encryption and data hiding can be completely independent, and images can be fully restored. Experimental results show that our approach is highly flexible and has a higher amount of embedding compared to those of other related works. [ABSTRACT FROM AUTHOR]

Shape recognition is a main challenging problem in computer vision. Different approaches and tools are used to solve this problem. Most existing approaches to object recognition are based on pixels. Pixel-based methods are dependent on the geometry and nature of the pixels, so the destruction of pixels reduces their performance. In this paper, we construct a graph that captures the topological and geometrical properties of the object. Then, using the coordinate and relation of its vertices, we extract features that are robust with respect to noise, rotation, scale variation and articulation. To evaluate our method, we provide different comparisons with state-of-the-art results on various known benchmarks, including Kimia's, Tari56, Tari1000, Tetrapod and articulated datasets. We provide the analysis of our method against different variations. The results confirm the advantage of this method in different datasets, especially in the presence of noise. [ABSTRACT FROM AUTHOR]

One important task of analyzing remote sensing satellite imagery is to categorize the pixels according to various landcover regions. This unsupervised segmentation task can be posed as a problem of pixel intensity clustering, considering the different spectral bands as different features. Due to the presence of noise and overlapping clusters present in remote sensing images, fuzzy clustering is popularly applied for the segmentation task. However, fuzzy C-means like fuzzy clustering algorithms suffer from random initialization that often causes them to get stuck into some local optimum results. In this article, a game theory-motivated approach based on Shapley value to initialize the cluster centers for FCM clustering has been adopted which provides more stability and improved performance. The proposed method explores and exploits the advantages of both game theory and fuzzy technique for pixel classification. The superiority of the approach has been demonstrated over a numeric satellite image data set as well as different real-life remote sensing satellite images both visually and numerically with statistical support. The results have been compared with several popular centroid-based clustering techniques, viz. K-means, K-means++, fuzzy C-means (FCM) and probabilistic FCM, using J m and I indexes as well as visual cluster plots. [ABSTRACT FROM AUTHOR]

In 2015, Lu proposed the (k, F1) interpolation-based reversible hiding scheme by using the center folding strategy (CFS) to improve the image quality of the interpolation neighboring pixels scheme. In Lu's scheme, k is used to define the total number of thresholds for categories of the complexity of the block, and F1 is the length of the secret message that can be concealed in the smoothest area. The hiding performance of Lu's scheme for the smooth image is great. However, the results of that scheme for complex images can still be improved. Therefore, this paper proposed an enhanced interpolation-based hiding scheme by modifying the structure of the CFS from having a single layer to having multiple layers. The secret data are encoded by the multiple-layer folding table to reduce the distortion between the original image and the stego-image. Experimental results show that the image quality and the payload of the proposed scheme are better than those of the other schemes. [ABSTRACT FROM AUTHOR]

In remote sensing, land cover classification of vegetation and water area from satellite image play a vital role for rural and urban planning and development. Existing algorithms of land cover classification require more sample image datasets for training. For existing algorithms, land cover classification of vegetation and water area is a challenging task because of mixed pixel and geometric distortion over boundary and curvature region. Mixed pixel affects the precise classification and measurement of land cover. Geometric distortion arises due to frame of isotropic and angular selectivity during image acquisition and affects the contour of land cover. In this paper, the proposed transverse dyadic wavelet transform (TDyWT) enhances and classifies vegetation and water area in land cover from LANDSAT image without training datasets. The proposed TDyWT uses Haar wavelet for decomposition and Burt 5 × 7 wavelet for reconstruction. The TDyWT enhances the contour, curvature, and boundary of vegetation and water area in LANDSAT image due to reversible and lifting properties of wavelet. TDyWT removes geometric distortion and spatial scale error of mixed pixel. In traditional land surveying spatial scale error reduction eliminates through total station and error modeling techniques. From the results, the proposed TDyWT algorithm classifies the area of subclass of vegetation and water with the 95% of accuracy with respect to ground truth survey methods. [ABSTRACT FROM AUTHOR]

To improve the anti-noise ability of credibilistic intuitionistic fuzzy c-means clustering method (CIFCM) for image segmentation, this paper proposes a robust credibilistic intuitionistic fuzzy c-means clustering method based on credibility of pixels and intuitionistic fuzzy entropy. Firstly, a new similarity measure is constructed by utilizing the grayscale and spatial relationship between the current pixel and its neighborhood pixels. Secondly, it is embedded into the objective function of credibilistic intuitionistic fuzzy c-means clustering, and a new robust clustering method with spatial constraints is presented to effectively solve the segmentation problem of image corrupted by high noise. In the end, the convergence of this proposed robust clustering method is strictly proved by iterated convergence theorem. Experimental results show that proposed algorithm has better noise-suppression ability and more satisfactory segmentation results than CIFCM algorithm. [ABSTRACT FROM AUTHOR]

This paper proposes a general multi-objective thresholding segmentation methodology for color images and a quality metric designed to prevent and quantify the overlapping effect of segmented images. Multi-level thresholding (MTH) has been used to segment color images in recent years; this process considers each channel as a single grayscale image and applies the MTH independently. Although this method provides competitive results, the inherent relationship among color channels is disregarded. Such approaches generate spurious classes on overlapping regions, where new colors are generated, especially on the borders of the objects. The proposed multi-objective color thresholding (MOCTH) approach performs image segmentation while preserving the relationship between image channels. MOCTH is aimed to reduce the overlapping effect on segmented color images without performing additional post-processing. To measure the overlapping classes on a thresholded color image, the overlapping index is proposed to quantify the pixels affected. The presented approach is analyzed on two color spaces (RGB and CIE L*a*b*) using three multi-objective algorithms; they are NSGA-III, SPEA-2, and MOPSO. Results provide evidence pointing out to a better segmentation from MOCTH over the traditional single-objective approaches while reducing overlapped areas on the image. [ABSTRACT FROM AUTHOR]

Low-rank decomposition (LRD) is an effective scheme to explore the affinity among superpixels in the image and video segmentation. However, the superpixel feature collected based on colour, shape, and texture may be rough, incompatible, and even conflicting if multiple features extracted in various manners are vectored and stacked straight together. It poses poor correlation, inconsistence on intra-category superpixels, and similarities on inter-category superpixels. This paper proposes a correlation-enhanced superpixel for video segmentation in the framework of LRD. Our algorithm mainly consists of two steps, feature analysis to establish the initial affinity among superpixels, followed by construction of a correlation-enhanced superpixel. This work is very helpful to perform LRD effectively and find the affinity accurately and quickly. Experiments conducted on datasets validate the proposed method. Comparisons with the state-of-the-art algorithms show higher speed and more precise in video segmentation. [ABSTRACT FROM AUTHOR]

This paper suggests a two-phase scheme for the impulse noise removal. In the first phase, an adaptive median filter (AMF) identifies noise candidates created by salt-and-pepper method. In the second phase, a new trust-region phase recovers noise pixels detected by the first phase. The trust-region phase produces a new adaptive radius strategy using the projected gradient for the cases where iterations are successful and a low-memory nonmonotone spectral projected gradient method (SPG) where iterations are unsuccessful. We solve the trust-region subproblem without bound constraints by the dogleg strategy (DG) using the structure of the compact limited memory Broyden–Fletcher–Goldfarb–Shanno technique. The solution is then projected into the boundary region. Numerical results are given to illustrate the efficiency of the new approach for the impulse noise removal. [ABSTRACT FROM AUTHOR]

Due to the limitation of depth of focus, we cannot capture images with all objects in focus. Such images always lose some information, limiting their application. In recent years, with the wide application of dual-camera devices, we can easily acquire multifocus images of the same scene. Image fusion methods can be used to integrate these multifocus images into a fused image, which preserves specific features, and have more information. In this article, we use the patches instead of the pixels as the processing unit and process each patch in the spatial domain. In addition, diverse features of patches are fed into random forest to obtain fidelity scores, which used to measure the clarity of patches. Finally, hidden Markov model is used to consider compatibility between adjacent patches. From the perspective of visual effects and quantitative evaluations, the proposed method has better results than many previous fusion methods. [ABSTRACT FROM AUTHOR]

Inspired by reversible data hiding methods that applied the PE (predicted error) strategy will have the advantage of good performances. It means that the closer the PE approaches its climax, the higher embedding capacity and image quality will have. This paper provides four stages of two-phase reversible data hiding method to produce prediction images with Lagrange interpolation on odd and even pixels, and to hide confidential information into the differences between the predicted image and the original image. Lagrange interpolation will be crossly applied on odd and even pixels to produce predicted images, and then histogram shifting modification will be applied to embed secret data into. The experimental results demonstrate the quality of Lena image from this scheme has a PSNR value of 43.97 dB and an embedding capacity of 0.38 bpp, for one level. For enhancing the embedding capacity to 0.98 bpp, our scheme can still maintain a PSNR value of 31.14 dB. From the demonstrated results, it can be obvious to know that our proposed algorithm has superior performances in terms of image quality and embedding capacity than that the algorithms of Ni et al. and Tai et al. [ABSTRACT FROM AUTHOR]

In this paper, we present a robust and imperceptible image steganography (IS) scheme for covert communication. A substantial literature presented on IS is distortion based that radically affects image imperceptibility. These schemes conceal secret information in LSBs or MSBs of cover image by using simple or random substitution. The usage of LSBs and MSBs makes these schemes vulnerable to malicious attacks like Chi-square attack and sample pair attack, and specifically, the MSBs affect the imperceptibility of cover image. Additionally, these schemes endure low capacity as large numbers of cover image pixels are required for hiding even low volume of information. The proposed IS scheme is distortion free as the negligible PVD of cover and secret image is utilized for information hiding. In contrast to LSB- or MSB-based information hiding schemes, we proposed FEM method that compares the entropy of frequencies of secret and cover image for information hiding. In fact, the elevated rate of FEM leads to high imperceptibility and capacity. Moreover, the proposed scheme uses multilayer approach that has layered transformations to frequency domain for improved robustness. Experimental investigation demonstrates that the proposed scheme has better PSNR and BPP with enhanced robustness and imperceptibility in contrast to existing schemes. [ABSTRACT FROM AUTHOR]

Multi-scale transforms (MST)-based methods are popular for multi-focus image fusion recently because of the superior performances, such as the fused image containing more details of edges and textures. However, most of MST-based methods are based on pixel operations, which require a large amount of data processing. Moreover, different fusion strategies cannot completely preserve the clear pixels within the focused area of the source image to obtain the fusion image. To solve these problems, this paper proposes a novel image fusion method based on focus-region-level partition and pulse-coupled neural network (PCNN) in nonsubsampled contourlet transform (NSCT) domain. A clarity evaluation function is constructed to measure which regions in the source image are focused. By removing the focused regions from the source images, the non-focus regions which contain the edge pixels of the focused regions are obtained. Next, the non-focus regions are decomposed into a series of subimages using NSCT, and subimages are fused using different strategies to obtain the fused non-focus regions. Eventually, the fused result is obtained by fusing the focused regions and the fused non-focus regions. Experimental results show that the proposed fusion scheme can retain more clear pixels of two source images and preserve more details of the non-focus regions, which is superior to conventional methods in visual inspection and objective evaluations. [ABSTRACT FROM AUTHOR]

Fuzzy C-means has been adopted for image segmentation, but it is sensitive to noise and other image artifacts due to not considering neighbor information. In order to solve this problem, many improved algorithms have been proposed, such as fuzzy local information C-means clustering algorithm (FLICM). However, the segmentation results of FLICM are unsatisfactory when performed on complex images. To overcome this, a novel fuzzy clustering algorithm is proposed in this paper, and more information is utilized to guide the procedure of image segmentation. In the proposed algorithm, pixel relevance based on patch similarity will be investigated firstly, by which all information over the whole image can be considered, not limited to local context. Compared with Zhang et al. (Multimed Tools Appl 76(6):7869–7895, 2017a. 10.1007/s11042-016-3399-x) pixel relevance is unnecessary to be normalized, and much more information can play positive role in image segmentation. Experimental results show that the proposed algorithm outperforms current fuzzy algorithms, especially in enhancing the robustness of corresponding fuzzy clustering algorithms. [ABSTRACT FROM AUTHOR]

Iris detection fails at the iris localization stage pulling out of the sub-image from the original image; the objective of this paper is to realize the narrative approach for iris localization and to solve the localization problem in an image using a dominant localization max-min algorithm which increases accuracy and reduces the search time. In the proposed system Zadeh dominated fuzzy rule composition algorithm was used to create the dominant values by comparing the values with the neighbours in the meticulous route. This algorithm helps to localize the iris image with a precision of 98.6% and a search time of 8.4 ms. [ABSTRACT FROM AUTHOR]

Fuzzy set theory has developed a prolific armamentarium of mathematical tools for each of the topics that has fallen within its scope. One of such topics is data comparison, for which a range of operators has been presented in the past. These operators can be used within the fuzzy set theory, but can also be ported to other scenarios in which data are provided in various representations. In this work, we elaborate on notions for type-2 fuzzy sets, specifically for the comparison of type-2 fuzzy membership degrees, to create function comparison operators. We further apply these operators to hyperspectral imaging, in which pixelwise data are provided as functions over a certain energy spectra. The performance of the functional comparison operators is put to the test in the context of in-laboratory hyperspectral image segmentation. [ABSTRACT FROM AUTHOR]

Transform-based techniques partially address challenges like robustness and the imperceptibility in image steganography. Such approaches, however, increase the memory requirement and reduce the quality of the cover image and hiding capacity. Moreover, the steganography is always coupled with cryptography to strengthen the confidentiality. This paper presents an adaptive hybrid method for image steganography procedure based on bit reduction and pixel adjustment using the fuzzy logic and integer wavelet transform technique. The fuzzy set theory provides powerful tools to represent and process human knowledge in the form of fuzzy if-then rules that can resolve difficulties in image processing arising due to the uncertainty of the data, tasks, and results. We apply a bit reduction algorithm to each byte of the data which are to hide in the cover image. This decreases the memory usage and increases the capacity. The embedding of the input text into the cover image distorts the cover image. Hence, to minimize the visual difference between the cover image and the text embedded image, an optimum pixel adjustment algorithm is applied to the text embedded image. Simulation results demonstrate the effectiveness of our proposed approach. [ABSTRACT FROM AUTHOR]

In this paper, we introduce the concepts of stratified fuzzy soft topogenous, stratified fuzzy soft filter, stratified fuzzy soft quasi-proximity and stratified fuzzy soft grill. Also, we introduce the concept of fuzzy soft topogenous structures by combining fuzzy soft topogenous with fuzzy soft filter and we introduce the concept of fuzzy soft quasi-proximity by combining fuzzy soft quasi-proximity with fuzzy soft grill and give their properties. Furthermore, we establish the relationship among these fuzzy soft topological structures and their stratifications. [ABSTRACT FROM AUTHOR]

In this paper, we introduce an intra-field deinterlacing algorithm based on a wavelet-content-adaptive back propagation (BP) neural network (BP-NN) using pixel classification. During interpolation, there is an issue of different image features having completely different properties, such as smooth regions, edges, and textures. We use the wavelet transform to divide the images into several pieces with different properties. Then, each piece has similar image features and each one is assigned to one neural network. The BP-NN-based deinterlacing algorithm can reduce blurring by recovering the missing pixels via a learning process. Compared with existing deinterlacing algorithms, the proposed algorithm improves the peak signal-to-noise ratio and visual quality while maintaining high efficiency. [ABSTRACT FROM AUTHOR]

Impulse noise, also known as impulsive noise, is one of the most common types of noise occurring in digital images. The median filter and morphological filters are often used to remove impulsive noise, but these filters do not preserve image details. In this paper, we first apply the median filter in order to reduce the amount of impulsive noise in a corrupted image. After an application of the direct fuzzy transform (FT) to the resulting image, we restored the pixel values corresponding to locations flagged by the fuzzy rule-based noise detector by means of the inverse fuzzy transform. Finally, we obtained the output of our proposed image filter by combining the restored pixels with the ones marked as noiseless by the aforementioned noise fuzzy detector. We compared the results of our approach that we called adaptive FT-based image filter (AFT-IF) with the ones obtained by a number of other image filters for impulsive noise reduction. [ABSTRACT FROM AUTHOR]

Pixel unmixing is essential for the reliable description of many land-cover patterns with low spatial resolution. The fuzzy ARTMAP neural network-based model has been proven effective for pixel unmixing in the literature. In most cases, the forms of the endmember combination in diverse pixels are very distinct. However, traditional fuzzy ARTMAP model neglects such difference and models endmembers as fixed composition entities. Due to this limitation, the mixture model is unable to precisely and effectively represent details in the result image. In this work, we address this issue by applying a new selective endmember spectral mixture model based on fuzzy ARTMAP neural network. We first consider the endmember variability and identify the most suitable form of the endmember combination, and then the fuzzy ARTMAP model is used to perform the unmixing work. Through two experiments, we show that a more accurate endmember combination in the parent pixel results in an adaptive representation image. The results confirm that the proposed algorithm can effectively improve the accuracy of the unmixing results compared with the linear unmixing method and the traditional fuzzy ARTMAP model. [ABSTRACT FROM AUTHOR]

This paper presents a novel framework for dynamic textures (DTs) modeling and recognition, investigating the use of chaotic features. We propose to extract chaotic features from each pixel intensity series in a video. The chaotic features in each pixel intensity series are concatenated to a feature vector, chaotic feature vector. Then, a video is modeled as a feature vector matrix. Next, two approaches of DTs recognition are investigated. A bag of words approach is used to represent each video as a histogram of chaotic feature vector. The recognition is carried out by 1-nearest neighbor classifier. We also investigate the use of earth mover's distance (EMD) method. Mean shift clustering algorithm is employed to cluster each feature vector matrix. EMD method is used to compare the similarity between two videos. The output of EMD matrix whose entry is the matching score can be used to DTs recognition. We have tested our approach on four datasets and obtained encouraging results which demonstrate the feasibility and validity of our proposed methods. [ABSTRACT FROM AUTHOR]

Multilevel thresholding is the method applied to segment the given image into unique sub-regions when the gray value distribution of the pixels is not distinct. The segmentation results are affected by factors such as number of threshold and threshold values. Hence, this paper proposes different methods for determining optimal thresholds using optimization techniques namely GA, PSO and hybrid model. Parallel algorithms are also proposed and implemented for these methods to reduce the execution time. From the experimental results, it is inferred that proposed methods take less time for determining the optimal thresholds when compared with existing methods such as Otsu and Kapur methods. [ABSTRACT FROM AUTHOR]

In this article, we present an algorithm that can efficiently track the contour extracted from silhouette of the moving object of a given video sequence using local neighborhood information and fuzzy k-nearest-neighbor classifier. To classify each unlabeled sample in the target frame, instead of considering the whole training set, a subset of it is considered depending on the amount of motion of the object between immediate previous two consecutive frames. This technique makes the classification process faster and may increase the classification accuracy. Classification of the unlabeled samples in the target frame provides object (silhouette of the object) and background (non-object) regions. Transition pixels from the non-object region to the object silhouette and vice versa are treated as the boundary or contour pixels of the object. Contour or boundary of the object is extracted by connecting the boundary pixels and the object is tracked with this contour in the target frame. We show a realization of the proposed method and demonstrate it on eight benchmark video sequences. The effectiveness of the proposed method is established by comparing it with six state of the art contour tracking techniques, both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

Fuzzy clustering algorithm is a frequently used method for image segmentation, which allows pixel to be classified into one or more clusters with respect to its membership level. However, its segmentation performance often suffered from the factors associated with the drift of cluster centers and the sensitiveness to the intensity overlap of distribution between classes. In this paper, we solve these drawbacks and present a modified strategy of fuzzy clustering algorithm for image segmentation. This strategy generally consists of two-pass processes. The first process is to directly calculate the cluster centers from the segmented image and then take the higher value of cluster centers as an alternative threshold to prevent the pixels with lower intensity from clustering. The second process thereby makes use of the fuzzy clustering algorithm with a bias field for partitioning pixels with spatial proximity, ensuring that our method is less sensitive to the drawbacks inherent in the fuzzy clustering algorithm and thus obtaining promising results. Experiments on synthetic and some representative infrared images demonstrate that the proposed method outperforms fuzzy c-means methods and its existing variants in terms of segmentation performance, and is less sensitive to the intensity overlap of the distribution between classes. [ABSTRACT FROM AUTHOR]

In edge detection, constructing features with rich responses on different types of edges is a challenging problem. Genetic programming (GP) has been previously employed to construct features. Normally, the values of the features constructed by GP are calculated from raw observations. Some existing work has considered the distributions of the raw observations, but these features only poorly indicate class label probabilities. To construct features with rich responses on different types of edges, the distributions of the observations from GP programs are investigated in this study. The values of the constructed features are obtained from estimated distributions, rather than directly using the observations. These features themselves indicate probabilities for the target labels. Basic rotation-invariant features from gradients, image quality, and local histograms are used to construct new composite features. The results show that the invariant features constructed by GP combine advantages from the basic features, reduce drawbacks from basic features alone, and improve the detection performance. In terms of the quantitative and qualitative evaluations, features constructed by GP with distribution estimation are better than the combinations from a Bayesian model and a linear support vector machine approach. [ABSTRACT FROM AUTHOR]

In this work, we axiomatically describe the concepts of total homogeneity and local homogeneity of a fuzzy set. We also present different construction methods by means of restricted equivalence functions, restricted dissimilarity functions and implication operators. We show that the most common homogeneity expressions can be obtained as particular cases of the constructions developed here. The usefulness of these functions is shown in segmentation of fingerprint images. [ABSTRACT FROM AUTHOR]

Image processing represents a research field in which high-quality solutions have been obtained using various soft computing techniques. Evolutionary algorithms constitute a class of stochastic search methods that are applicable in both optimization and design tasks. In the area of circuit design Cartesian Genetic Programming has often been utilized in combination with an algorithm of Evolutionary Strategy. Digital image filters represent a specific class of circuits whose design can be performed by means of this approach. Switching filters are advanced non-linear filtering techniques in which the main idea is to detect and filter the noise pixels while keeping the uncorrupted pixels unchanged in order to increase the quality of the resulting image. The aim of this article is to present a robust design technique based on Cartesian Genetic Programming for the automatic synthesis of switching image filters intended for real-time processing applications. The robustness of the proposed evolutionary approach is evaluated using four design problems including the removal of salt and pepper noise, random shot noise, impulse burst noise and impulse burst noise combined with random shot noise. An extensive evaluation is performed in order to compare the properties of the evolved switching filters with the best conventional solutions. The evaluation has shown that the evolved switching filters exhibit a very good trade off between the quality of filtering and the implementation cost in field programmable gate arrays. [ABSTRACT FROM AUTHOR]

This paper investigates automatic video temporal segmentation techniques, also named shot boundary detection (SBD) techniques. Firstly, the existing SBD algorithms are reviewed in detail. Then, a new SBD algorithm is proposed aiming to obtain fast and accurate detection, and its performances are evaluated and compared with existing works. This algorithm computes the frame difference/similarity by such simple features as pixel difference and histogram difference, adopts motion-based difference to resist camera or object movements in the same shot and uses the flash detection to avoid false positives caused by light changes or flashes. The adopted features are computational efficient, and the combination of various features improve the detection accuracy. These properties make the algorithm suitable for real-time applications, such as broadcasted news segmentation. [ABSTRACT FROM AUTHOR]