Search

Depth information has been discovered to improve the performance of computer vision tasks, such as semantic segmentation and object recognition. However, careful acquisition of depth data needs highly developed depth sensors which are expensive. As a classic computer vision task, depth estimation from a single image has obtained promising results based on supervised learning methods. In this paper, we investigate the extension of color images with corresponding deep-regressed depth images in boosting the performance of semantic segmentation. Furthermore, the usage of combining color channels with the estimated depth or the ground truth depth channel is compared. Specifically, there are two stages in our work. Firstly, we adopt the framework of convolutional neural networks (CNN) for the depth estimation by combing the global depth network and the depth gradient network. After refining based on these two networks, the depth image map can be estimated in a deep-regressed manner. Secondly, after augmenting the color images with the predicted depth images, fully convolutional networks (FCN) are further used to implement the pixel-level semantic labeling. In the experiments, we employ two popular RGBD datasets, i.e., SUNRGBD and NYUDv2, for 37 and 40-class semantic segmentation, respectively. By comparing with the ground truth depth images, experimental results demonstrate that the networks trained on the estimated depth images can achieve comparable performance on facilitating the accuracy of semantic segmentation task. [ABSTRACT FROM AUTHOR]

Introduced in the mid-1970s as an intermediate step in proving a long-standing conjecture on arithmetic progressions, Szemerédi’s regularity lemma has emerged over time as a fundamental tool in different branches of graph theory, combinatorics and theoretical computer science. Roughly, it states that every graph can be approximated by the union of a small number of random-like bipartite graphs called regular pairs. In other words, the result provides us a way to obtain a good description of a large graph using a small amount of data, and can be regarded as a manifestation of the all-pervading dichotomy between structure and randomness. In this paper we will provide an overview of the regularity lemma and its algorithmic aspects, and will discuss its relevance in the context of pattern recognition research. [ABSTRACT FROM AUTHOR]

In this paper, we propose a spectral graph wavelet approach for 3D shape retrieval using the bag-of-features paradigm. In an effort to capture both local and global characteristics of a 3D shape, we present a three-step feature description framework. Local descriptors are first extracted via the spectral graph wavelet transform having the Mexican hat wavelet as a generating kernel. Then, mid-level features are obtained by embedding local descriptors into the visual vocabulary space using the soft-assignment coding step of the bag-of-features model. A global descriptor is subsequently constructed by aggregating mid-level features weighted by a geodesic exponential kernel, resulting in a matrix representation that describes the frequency of appearance of nearby codewords in the vocabulary. Then, we compare the global descriptor of a query to all global descriptors of the shapes in the dataset using a dissimilarity measure and find the closest shape. Experimental results on two standard 3D shape benchmarks demonstrate the effectiveness of the proposed shape retrieval approach in comparison with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Hierarchies, such as the tree of shapes, are popular representations for image simplification and segmentation thanks to their multiscale structures. Selecting meaningful level lines (boundaries of shapes) yields to simplify image while preserving intact salient structures. Many image simplification and segmentation methods are driven by the optimization of an energy functional, for instance the celebrated Mumford–Shah functional. In this paper, we propose an efficient approach to hierarchical image simplification and segmentation based on the minimization of the piecewise-constant Mumford–Shah functional. This method conforms to the current trend that consists in producing hierarchical results rather than a unique partition. Contrary to classical approaches which compute optimal hierarchical segmentations from an input hierarchy of segmentations, we rely on the tree of shapes, a unique and well-defined representation equivalent to the image. Simply put, we compute for each level line of the image an attribute function that characterizes its persistence under the energy minimization. Then we stack the level lines from meaningless ones to salient ones through a saliency map based on extinction values defined on the tree-based shape space. Qualitative illustrations and quantitative evaluation on Weizmann segmentation evaluation database demonstrate the state-of-the-art performance of our method. [ABSTRACT FROM AUTHOR]

Shape clustering is a difficult visual task due to large intra-class variations and small inter-class variations induced by shape articulation, rotation, occlusion, etc . To tackle this problem, we attempt to leverage the complementary nature among features of different statistics ( e.g. , skeleton-based descriptors and contour-based descriptors) for robust clustering. In this paper, a similarity fusion framework based on spectral analysis is proposed. The proposed method, which we call co-spectral, is a spectral clustering algorithm. It has two inborn merits for shape clustering: (1) it can automatically make use of the complementarity of various shape similarities based on a co-training framework; (2) it does not require shape representations to be vectors. Co-spectral is evaluated on several popular shape benchmarks. The experimental results demonstrate that co-spectral outperforms the state-of-the-art algorithms by a large margin. [ABSTRACT FROM AUTHOR]

In this paper, we propose a method for classification of human actions using pose based features. We demonstrate that statistical information of key movements of actions can be utilized in designing an efficient input representation, using fuzzy membership functions. The ability of stacked auto encoder to learn the underlying features of input data is exploited to recognize human actions. The efficacy of the proposed approach is demonstrated on CMU MOCAP and Berkeley MHAD datasets. [ABSTRACT FROM AUTHOR]

Defining and computing distances between tree structures is a classical area of study in theoretical computer science, with practical applications in the areas of computational biology, information retrieval, text analysis, and many others. In this paper, we focus on rooted, unordered, uniquely-labelled trees such as taxonomies and other hierarchies. For trees as these, we introduce the intuitive concept of a ‘local move’ operation as an atomic edit of a tree. We then introduce SuMoTED, a new edit distance measure between such trees, defined as the minimal number of local moves required to convert one tree into another. We show how SuMoTED can be computed using a scalable algorithm with quadratic time complexity. Finally, we demonstrate its use on a collection of music genre taxonomies. [ABSTRACT FROM AUTHOR]

Visual secret sharing (VSS) scheme is a perfect secure method that protects a secret image by breaking it into shadow images (called shadows). Unlike other threshold schemes, VSS scheme can be easily decoded by the human visual system without the knowledge of cryptography and cryptographic computations. However, the size of shadow images (i.e., the number of columns of the black and white matrices in VSS scheme [Naor, Shamir, Visual cryptography, Advances in Cryptology-EUROCRYPT’94, Lecture Notes in Computer Science, vol. 950, Springer-Verlag, 1995, p. 1]) will be expanded. Most recent papers about VSS schemes are dedicated to get a higher contrast or a smaller shadow size.In this paper, we use the frequency of white pixels to show the contrast of the recovered image. Our scheme is non-expansible and can be easily implemented on a basis of conventional VSS scheme. The term non-expansible means that the sizes of the original image and shadows are the same. [Copyright &y& Elsevier]

Community detection in a social network is a well-known problem that has been studied in computer science since early 2000. The algorithms available in the literature mainly follow two strategies, one, which allows a node to be a part of multiple communities with equal membership, and the second considers a disjoint partition of the whole network where a node belongs to only one community. In this paper, we proposed a novel community detection algorithm which identifies fuzzy-rough communities where a node can be a part of many groups with different memberships of their association. The algorithm runs on a new framework of social network representation based on fuzzy granular theory. A new index viz. normalized fuzzy mutual information, to quantify the goodness of detected communities is used. Experimental results on benchmark data show the superiority of the proposed algorithm compared to other well known methods, particularly when the network contains overlapping communities. [ABSTRACT FROM AUTHOR]

Highlights: [•] A novel classification technique based on transductive SVM learning is presented. [•] The paper pointed out the drawbacks of the existing literature methods. [•] To mitigate drawbacks, here we exploit SVM, k-nn classifiers and cluster assumption. [•] Results were compared with two other TSVM methods existing in the literature. [•] Experimental results confirmed the effectiveness of the proposed technique. [Copyright &y& Elsevier]

Abstract: Recently, classification tasks that naturally emerge in multi-label domains, such as text categorization, automatic scene annotation, and gene function prediction, have attracted great interest. As in traditional single-label classification, feature selection plays an important role in multi-label classification. However, recent feature selection methods require preprocessing steps that transform the label set into a single label, resulting in subsequent additional problems. In this paper, we propose a feature selection method for multi-label classification that naturally derives from mutual information between selected features and the label set. The proposed method was applied to several multi-label classification problems and compared with conventional methods. The experimental results demonstrate that the proposed method improves the classification performance to a great extent and has proved to be a useful method in selecting features for multi-label classification problems. [Copyright &y& Elsevier]

Abstract: Multi-label learning refers to methods for learning a classification function that predicts a set of relevant labels for an instance. Label embedding seeks a transformation which maps labels into a latent space where regression is performed to predict a set of relevant labels. The latent space is often a low-dimensional space, so computational and space complexities are reduced. However, the choice of an appropriate transformation to a latent space is not clear. In this paper we present a max-margin embedding method where both instances and labels are mapped into a low-dimensional latent space. In contrast to existing label embedding methods, the pair of instance and label embeddings is determined by minimizing a cost-sensitive multi-label hinge loss, in which label-dependent cost is applied to more penalize the misclassification of positive examples. For implementation, we employ the limited memory Broyden–Fletcher–Goldfarb–Shanno (BFGS) method to determine the instance and label embeddings by a joint optimization. Numerical experiments on a few datasets demonstrate the high performance of our method compared to existing embedding methods in the case where the dimensionality of the latent space is much smaller than that of the original label space. [Copyright &y& Elsevier]

Abstract: Chemoinformatics is a well established research field concerned with the discovery of molecule’s properties through informational techniques. Computer science’s research fields mainly concerned by chemoinformatics are machine learning and graph theory. From this point of view, graph kernels provide a nice framework combining machine learning and graph theory techniques. Such kernels prove their efficiency on several chemoinformatics problems and this paper presents two new graph kernels applied to regression and classification problems. The first kernel is based on the notion of edit distance while the second is based on subtrees enumeration. The design of this last kernel is based on a variable selection step in order to obtain kernels defined on parsimonious sets of patterns. Performances of both kernels are investigated through experiments. [Copyright &y& Elsevier]

Abstract: In the traditional secret image sharing schemes, the shadow images are generated by embedding the secret data into the cover image such that a sufficient number of shadow images can cooperate to reconstruct the secret image. In the process of reconstruction, each shadow image plays an equivalent role. However, a general threshold access structure could have other useful properties for the application. In this paper, we consider the problem of secret shadow images with a hierarchical threshold structure, employing Tassa’s hierarchical secret sharing to propose a hierarchical threshold secret image sharing scheme. In our scheme, the shadow images are partitioned into several levels, and the threshold access structure is determined by a sequence of threshold requirements. If and only if the shadow images involved satisfy the threshold requirements, the secret image can be reconstructed without distortion. [Copyright &y& Elsevier]

Abstract: Face recognition has been a long standing problem in computer vision. Recently, Histograms of Oriented Gradients (HOGs) have proven to be an effective descriptor for object recognition in general and face recognition in particular. In this paper, we investigate a simple but powerful approach to make robust use of HOG features for face recognition. The three main contributions of this work are: First, in order to compensate for errors in facial feature detection due to occlusions, pose and illumination changes, we propose to extract HOG descriptors from a regular grid. Second, fusion of HOG descriptors at different scales allows to capture important structure for face recognition. Third, we identify the necessity of performing dimensionality reduction to remove noise and make the classification process less prone to overfitting. This is particularly important if HOG features are extracted from overlapping cells. Finally, experimental results on four databases illustrate the benefits of our approach. [Copyright &y& Elsevier]

Abstract: The present paper considers the problem of partitioning a dataset into a known number of clusters using the sum of squared errors criterion (SSE). A new clustering method, called DE-KM, which combines differential evolution algorithm (DE) with the well known K-means procedure is described. In the method, the K-means algorithm is used to fine-tune each candidate solution obtained by mutation and crossover operators of DE. Additionally, a reordering procedure which allows the evolutionary algorithm to tackle the redundant representation problem is proposed. The performance of the DE-KM clustering method is compared to the performance of differential evolution, global K-means method, genetic K-means algorithm and two variants of the K-means algorithm. The experimental results show that if the number of clusters K is sufficiently large, DE-KM obtains solutions with lower SSE values than the other five algorithms. [Copyright &y& Elsevier]

Abstract: Image splicing is very common and fundamental in image tampering, which severely threatens the integrity and authenticity of images. As a result, the detection of image splicing is of great importance. In this paper, an approximate run length based scheme is proposed to detect this specific artifact. Firstly, the edge gradient matrix of an image is computed, and approximate run length is calculated along the edge gradient direction. Then, some features are constructed from the histogram of the approximate run length. To further improve the detection accuracy, the approximate run length is applied on the predict-error image and the reconstructed images based on DWT to obtain more features. Finally, support vector machine (SVM) is exploited to classify the authentic and spliced images using the constructed features. The experiment results demonstrate that the proposed approach can achieve a relatively high accuracy with less computational cost and fewer features when compared with other methods. [Copyright &y& Elsevier]

Abstract: In this paper, we propose an approach to quantitative structural information for inferring context free grammars. First, we construct derivative capacity of nonterminal symbols in context free grammar, concomitant indicator and embedded dimensional number of strings in samples set, which are called as quantitative structural information; then, we rewrite Cocke–Younger–Kasami (CYK) algorithm for parsing in the form of the derivative set; third, we present the construction of new production rule and the descriptive procedure for inferring with an extended CYK algorithm by the quantitative structural information. Finally, we discuss the extended CYK algorithm for inferring context free grammars. [Copyright &y& Elsevier]

Abstract: In this paper, we present a simple but fast codebook generation algorithm, called PREGLA (Pattern Reduction Enhanced GLA). The proposed algorithm is fundamentally different from the previous approaches in that the previous approaches focus on reducing the size of the codebook whereas the proposed algorithm focuses on using pattern reduction to reduce the computation time. The proposed algorithm is motivated by the observation that input vectors that are “static” during the training process can be considered as part of the final solutions and thus can be compressed and removed to eliminate the redundant computations at the later iterations of the training process. To evaluate the performance of the proposed algorithm, we compare the proposed algorithm with “efficient” state-of-the-art GLA or GLA-based algorithms such as Codeword Displacement, Nearest Partition Set Search, Fast Vector Quantization Algorithm, Law of Cosines, and standard GLA. Our experimental results indicate that the proposed algorithm can reduce the computation time from 29.45% up to about 77.98% compared to those of standard GLA and other fast GLA-based algorithms alone. [Copyright &y& Elsevier]

Abstract: Among the SVM-based methods for multi-category classification, “1-a-r”, pairwise and DAGSVM are most widely used. The deficiency of “1-a-r” is long training time and unclassifiable region; the deficiency of pairwise and DAGSVM is the redundancy of sub-classifiers. We propose an uncertainty sampling-based multi-category SVM in this paper. In the new method, some necessary sub-classifiers instead of all N ×(N −1)/2 sub-classifiers are selected to be trained and the uncertainty sampling strategy is used to decide which samples should be selected in each training round. This uncertainty sampling-based method is proved to be accurate and efficient by experimental results on the benchmark data. [Copyright &y& Elsevier]

Abstract: Image restoration algorithms often require previous knowledge about the point spread function (PSF) of the disturbance. Deriving the PSF manually from a degraded ideal step-edge in the image is a well known procedure intended mainly for isotropic degradations. A common image degradation that can be approximated as isotropic is the atmospheric blurring in long-distance imaging. This paper proposes an efficient method that automatically finds the best (closest to ideal) step-edge from the degraded image. The identified PSF is then used to restore the image. The existence of a good step-edge in the image may be assumed in cases such as imaging of urban areas, which is common in applications such as visual surveillance and reconnaissance. The criteria employed include the straightness and length of the edge, its strength, and the homogeneity of the step. An efficient algorithm is proposed, and results of automatic blind image restoration based on the automatically extracted PSF are shown. [Copyright &y& Elsevier]

Abstract: In this paper a novel method to derive the Medial Axis of a shape is presented. The property that the Medial Axis is a subset of the Symmetry Set is used. The latter allows a formulation in terms of two equations, based on geometrical arguments. From the set that solves the equations, the subset that yields the Medial Axis can be taken. An algorithm is given that performs these tasks. The Medial Axis can easily be labelled with respect to main axis and branches, as this information follows directly from the Symmetry Set. [Copyright &y& Elsevier]

Abstract: In this paper we make the connection between two approaches for supervised classification with a rejection option. The first approach is due to Tortorella and is based on ROC curves and the second is a generalisation of Chow’s optimal rule. [Copyright &y& Elsevier]

Vector quantization (VQ) is an asymmetric coding method and the winner search in encoding process is extremely time-consuming. This property of VQ constrains its practical applications very much. Based on the sum pyramid data structure of a vector, a fast encoding algorithm with PSNR equivalent to full search is proposed in this paper to improve the results that have been given in [Pattern Recognition Lett. 22(3/4) (2001) 373].Three major modifications are made. Because sum can be computed accurately using integer operation, mismatched winners due to roundoff error of taking the mean can be overcome firstly by using sum instead of the mean. Secondly, since sum is computed by 2-pixel-merging other than 4-pixel-merging way, more levels can be constructed in a sum pyramid so that the rejection to current codeword can be realized easier. Finally, codebook is off-line rearranged by sorted real sums directly, and the lower and upper bound for promising codeword class are updated dynamically to narrow search scope further once a better-matched codeword has been found during winner search process.For the same four 512 × 512, 256-level standard test images, experimental results show that the proposed algorithm outperforms the method used in [Pattern Recognition Lett. 22(3/4) (2001) 373] in the meaning of total equivalent distance computation being reduced obviously. [Copyright &y& Elsevier]

In this paper, we contribute a new paradigm of combining string recognizers and propose generic frameworks for hierarchical and parallel combination of multiple string recognizers. The frameworks are open to any new achievement in either recognizers or combination algorithms, and can be applied to both machine-printed and handwritten string recognition problems. A parallel combination system, StrCombo, is implemented based on three independent alphanumeric handwritten string recognizers that act as black boxes. We propose a graph-based approach that regards each segment from individual string recognizers as nodes of a graph, and choose the optimal path with the lowest cost to output a combined result. All factors such as the agreement of size, classification, and the position are converted into a measurement resulting in a soft decision. StrCombo has achieved a substantial improvement over any one of the individual recognizers, as demonstrated by experimental results on standard numeral string databases and a non-standard alphanumeric string database from real-life applications. [Copyright &y& Elsevier]