Search

Cartoonization as a special type of artistic style transfer is a difficult image processing task. The current existing artistic style transfer methods cannot generate satisfactory cartoon-style images due to that artistic style images often have delicate strokes and rich hierarchical color changes while cartoon-style images have smooth surfaces without obvious color changes, and sharp edges. To this end, we propose a cartoon loss based generative adversarial network (CartoonLossGAN) for cartoonization. Particularly, we first reuse the encoder part of the discriminator to build a compact generative adversarial network (GAN) based cartoonization architecture. Then we propose a novel cartoon loss function for the architecture. It can imitate the process of sketching to learn the smooth surface of the cartoon image, and imitate the coloring process to learn the coloring of the cartoon image. Furthermore, we also propose an initialization strategy, which is used in the scenario of reusing the discriminator to make our model training easier and more stable. Extensive experimental results demonstrate that our proposed CartoonLossGAN can generate fantastic cartoon-style images, and outperforms four representative methods. [ABSTRACT FROM AUTHOR]

Preserving projection-based methods are good for finding the manifold structure embedded in data. As they use the Euclidean distance as a metric, which is sensitive to noise and outliers in data, nuclear norm-based 2D locality preserving projection (NN-2DLPP) is thus proposed to improve the robustness of 2DLPP. However, NN-2DLPP does not consider the discriminant ability of data. In order to improve the discriminant ability of preserving projection methods, in this paper, we use preserving projection learning with structurally incoherence of data and propose structurally incoherent low-rank 2DLPP (SILR-2DLPP) for image classification. This approach provides a discriminative representation of preserving projection learning by recovering the distinct different classes of the data. SILR-2DLPP searches the optimal subspace and low-rank representation simultaneously. We further extend SILR-2DLPP to a kernel case and propose kernel SILR-2DLPP (KSILR-2DLPP) to obtain a nonlinear representation. The theoretical analysis including the convergence and computational complexity of SILR-2DLPP are presented. To verify the performance of SILR-2DLPP and KSILR-2DLPP, six well-known image databases were used in the experiments. The experimental results show that the proposed methods are superior to the previous preserving projection methods for image classification. [ABSTRACT FROM AUTHOR]

Dynamic scene classification has been extensively studied in computer vision due to its widespread applications. The key to dynamic scene classification lies in jointly characterizing spatial appearance and temporal dynamics to achieve informative representation, which remains an outstanding task in the literature. In this paper, we propose a unified framework to extract spatial and temporal features for dynamic scene representation. More specifically, we deploy two variants of deep convolutional neural networks to encode spatial appearance and short-term dynamics into short-term deep features (STDF). Based on STDF, we propose using the autoregressive moving average model to extract long-term frequency features (LTFF). By combining STDF and LTFF, we establish the long–short-term feature (LSTF) representations of dynamic scenes. The LSTF characterizes both spatial and temporal patterns of dynamic scenes for comprehensive and information representation that enables more accurate classification. Extensive experiments on three-dynamic scene classification benchmarks have shown that the proposed LSTF achieves high performance and substantially surpasses the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

2-D linear discriminant analysis (2DLDA) has been widely used in pattern recognition and image classification. 2DLDA selects discriminative features from the up and left corner of images. However, 2DLDA uses the Frobenius norm (F-norm), which is sensitive to noise or outliers in data, as a metric. In this paper, we propose a novel framework, called horizontal and vertical nuclear norm-based 2DLDA (HVNN-2DLDA) for image representation. In the proposed framework, HVNN-2DLDA methods (i.e., HNN-2DLDA and VNN-2DLDA) are proposed, and both use the nuclear norm as a criterion. The nuclear norm can provide more structure and global information for the reconstruction of noisy images. HNN-2DLDA and VNN-2DLDA represent images in the row and column directions, respectively. In addition, by combining the row and column directions, we propose a bilateral nuclear norm-based 2DLDA method called BNN-2DLDA. The advantage of BNN-2DLDA over HNN-2DLDA and VNN-2DLDA is that an image sample can be represented by both the row and the column directions instead of only the row or column direction. HVNN-2DLDA learns a set of local optimal projection vectors by maximizing the ratio of the nuclear norm of the between-class scatter matrix and the nuclear norm of the within-class scatter matrix. To verify the robustness and recognition performance in image classification of HVNN-2DLDA, six public image databases are used for experiments. The experimental results demonstrate the effectiveness and the feasibility of the proposed framework. [ABSTRACT FROM AUTHOR]

Scene classification of remote sensing images has drawn great attention because of its wide applications. In this paper, with the guidance of the human visual system (HVS), we explore the attention mechanism and propose a novel end-to-end attention recurrent convolutional network (ARCNet) for scene classification. It can learn to focus selectively on some key regions or locations and just process them at high-level features, thereby discarding the noncritical information and promoting the classification performance. The contributions of this paper are threefold. First, we design a novel recurrent attention structure to squeeze high-level semantic and spatial features into several simplex vectors for the reduction of learning parameters. Second, an end-to-end network named ARCNet is proposed to adaptively select a series of attention regions and then to generate powerful predictions by learning to process them sequentially. Third, we construct a new data set named OPTIMAL-31, which contains more categories than popular data sets and gives researchers an extra platform to validate their algorithms. The experimental results demonstrate that our model makes great promotion in comparison with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Nonnegative matrix factorization (NMF), known as a famous matrix factorization technique, has been widely used in pattern recognition and computer vision. NMF represents the input data matrix as a product of two nonnegative factors. As NMF is based on the Euclidean distance, which is sensitive to noise or errors in the data, some robust NMF methods are proposed. Mainly focusing on parts-based representation, these robust NMF methods often neglect global representation of data. In fact, the global geometry information of data is more robust than the local information about the noisy data in terms of image classification. In order to effectively improve the robustness of NMF and learn part-based and global representation of the data, a novel method low-rank nonnegative factorization (LRNF) is proposed in this paper. First, we assume that the data are grossly corrupted, and the $L_{1} $ norm is used as a sparse constraint on the assumed noise matrix. Then, LRNF learns a low-rank matrix with the global representation ability. Finally, we make a nonnegative factorization of the learned low-rank matrix. We can obtain a base matrix, which preserves locality and globality properties of the data in the meantime. Extensive experiments have been conducted on nine real-world image databases to verify the performance of the proposed LRNF method by comparing with the state-of-the-art algorithms on robust dimensionality reduction. [ABSTRACT FROM AUTHOR]

Nonnegative matrix factorization (NMF) is one widely used feature extraction technology in the tasks of image clustering and image classification. For the former task, various unsupervised NMF methods based on the data distribution structure information have been proposed. While for the latter task, the label information of the dataset is one very important guiding. However, most previous proposed supervised NMF methods emphasis on imposing the discriminant constraints on the coefficient matrix. When dealing with new coming samples, the transpose or the pseudoinverse of the basis matrix is used to project these samples to the low dimension space. In this way, the label influence to the basis matrix is indirect. Although, there are also some methods trying to constrain the basis matrix in NMF framework, either they only restrict within-class samples or impose improper constraint on the basis matrix. To address these problems, in this article a novel NMF framework named discriminative and orthogonal subspace constraints-based nonnegative matrix factorization (DOSNMF) is proposed. In DOSNMF, the discriminative constraints are imposed on the projected subspace instead of the directly learned representation. In this manner, the discriminative information is directly connected with the projected subspace. At the same time, an orthogonal term is incorporated in DOSNMF to adjust the orthogonality of the learned basis matrix, which can ensure the orthogonality of the learned subspace and improve the sparseness of the basis matrix at the same time. This framework can be implemented in two ways. The first way is based on the manifold learning theory. In this way, two graphs, i.e., the intrinsic graph and the penalty graph, are constructed to capture the intra-class structure and the inter-class distinctness. With this design, both the manifold structure information and the discriminative information of the dataset are utilized. For convenience, we name this method as the name of the framework, i.e., DOSNMF. The second way is based on the Fisher's criterion, we name it Fisher's criterion-based DOSNMF (FDOSNMF). The objective functions of DOSNMF and FDOSNMF can be easily optimized using multiplicative update (MU) rules. The new methods are tested on five datasets and compared with several supervised and unsupervised variants of NMF. The experimental results reveal the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

Sufficient training examples are the fundamental requirement for most of the learning tasks. However, collecting well-labelled training examples is costly. Inspired by Zero-shot Learning (ZSL) that can make use of visual attributes or natural language semantics as an intermediate level clue to associate low-level features with high-level classes, in a novel extension of this idea, we aim to synthesise training data for novel classes using only semantic attributes. Despite the simplicity of this idea, there are several challenges. First, how to prevent the synthesised data from over-fitting to training classes? Second, how to guarantee the synthesised data is discriminative for ZSL tasks? Third, we observe that only a few dimensions of the learnt features gain high variances whereas most of the remaining dimensions are not informative. Thus, the question is how to make the concentrated information diffuse to most of the dimensions of synthesised data. To address the above issues, we propose a novel embedding algorithm named Unseen Visual Data Synthesis (UVDS) that projects semantic features to the high-dimensional visual feature space. Two main techniques are introduced in our proposed algorithm. (1) We introduce a latent embedding space which aims to reconcile the structural difference between the visual and semantic spaces, meanwhile preserve the local structure. (2) We propose a novel Diffusion Regularisation (DR) that explicitly forces the variances to diffuse over most dimensions of the synthesised data. By an orthogonal rotation (more precisely, an orthogonal transformation), DR can remove the redundant correlated attributes and further alleviate the over-fitting problem. On four benchmark datasets, we demonstrate the benefit of using synthesised unseen data for zero-shot learning. Extensive experimental results suggest that our proposed approach significantly outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Motion is an important clue for industrial inspection, video surveillance, and service machines to localize and recognize products and objects. Because blur co-occurs with motion, it is desirable for developing efficient and robust motion blur detection algorithm. However, existing algorithms are inefficient for detecting spatially varying motion blur. To deal with the problem, this paper presents a theorem, according to which, motion blur can be efficiently detected and segmented. According to the theorem, the proposed algorithm requires a simple filtering operation and variance computation. Classification as either blurred or unblurred pixel can be done by substituting the variance into the proposed simple formula and checking the sign of the resulting value. Moreover, a geometric interpretation and two extensions of the algorithm are given. Importantly, based on the geometric interpretation of the indicator function, we develop a one-class classifier, which is more effective than the indicator function and has comparable computational cost of the indicator function. Experimental results on detecting motion-blurred cars, motorcycles, bicycles, bags, and persons demonstrate that the proposed algorithm is very efficient without loss of effectiveness. [ABSTRACT FROM PUBLISHER]

We consider the problem of image representation from the perspective of statistical design. Recent studies have shown that images are possibly sampled from a low dimensional manifold despite of the fact that the ambient space is usually very high dimensional. Learning low dimensional image representations is crucial for many image processing tasks such as recognition and retrieval. Most of the existing approaches for learning low dimensional representations, such as principal component analysis (PCA) and locality preserving projections (LPP), aim at discovering the geometrical or discriminant structures in the data. In this paper, we take a different perspective from statistical experimental design, and propose a novel dimensionality reduction algorithm called A-Optimal Projection (AOP). AOP is based on a linear regression model. Specifically, AOP finds the optimal basis functions so that the expected prediction error of the regression model can be minimized if the new representations are used for training the model. Experimental results suggest that the proposed approach provides a better representation and achieves higher accuracy in image retrieval. [ABSTRACT FROM PUBLISHER]

A novel superpixel extraction algorithm using a higher order energy optimization framework is proposed in this paper. We first adopt the $k$ -means clustering technique to quickly get an initial superpixel result. Then a higher order energy function is employed to optimize and refine these initial superpixels. We use a more general higher order energy function that includes a first-order data term, a second-order smoothness term, and a higher order term. The presegments are employed to provide the prior information of sufficient edges and segment regions for our higher order energy term. According to the texture measurement in different local regions, our algorithm adaptively computes the proper ratios of different energy terms to obtain a better superpixel performance. The experimental results demonstrate that our method using the higher order energy generates better results with well-aligned boundaries and homogeneous effects than the existing superpixel algorithms. [ABSTRACT FROM PUBLISHER]

Supervoxels have been widely used as a preprocessing step to exploit object boundaries to improve the performance of video processing tasks. However, most of the traditional supervoxel algorithms do not perform well in regions with complex textures or weak boundaries. These methods may generate supervoxels with overlapping boundaries. In this paper, we present the novel video supervoxel generation algorithm using partially absorbing random walks to get more accurate supervoxels in these regions. Our spatial–temporal framework is introduced by making full use of the appearance and motion cues, which effectively exploits the temporal consistency in video sequence. Moreover, we build a novel Laplacian optimization structure using two adjacent frames to make our approach more efficient. Experimental results demonstrated that our method achieved better performance than the state-of-the-art supervoxel algorithms. [ABSTRACT FROM PUBLISHER]

Rapid growth of social media resources brings huge challenges and opportunities for image description technologies. The performance of image description method directly affects the accuracy of image retrieval, image annotation and image recognition. Bag of Words (BoW) as an efficient approach to describing the images has been attracting more and more attention. However, in traditional BoW, the maps between the words in the codebook and the features extracted from the images are actually ambiguous. As the Fuzzy Sets Theory (FST) is a powerful means for dealing with uncertainty efficiently, we utilize the FST to solve the problem caused by the ambiguity between the features and words. Accordingly, we propose a new type of BoW named as FBoW to describe images based on FST. Firstly, the features are extracted from the images. Secondly, k-means is utilized to learn the codebook. Thirdly, a fuzzy membership function is designed to measure the similarity between the features and words. The optimal parameters of the fuzzy membership function are obtained by using a Genetic Algorithm (GA). The histogram is generated by adding up the fuzzy membership values of each word to describe the images. The experimental results show that the proposed FBoW outperforms traditional BoW for social image description. [ABSTRACT FROM AUTHOR]

Fine-grained image categorization is a challenging task aiming at distinguishing objects belonging to the same basic-level category, e.g., leaf or mushroom. It is a useful technique that can be applied for species recognition, face verification, and so on. Most of the existing methods either have difficulties to detect discriminative object components automatically, or suffer from the limited amount of training data in each sub-category. To solve these problems, this paper proposes a new fine-grained image categorization model. The key is a dense graph mining algorithm that hierarchically localizes discriminative object parts in each image. More specifically, to mimic the human hierarchical perception mechanism, a superpixel pyramid is generated for each image. Thereby, graphlets from each layer are constructed to seamlessly capture object components. Intuitively, graphlets representative to each super-/sub-category is densely distributed in their feature space. Thus, a dense graph mining algorithm is developed to discover graphlets representative to each super-/sub-category. Finally, the discovered graphlets from pairwise images are integrated into an image kernel for fine-grained recognition. Theoretically, the learned kernel can generalize several state-of-the-art image kernels. Experiments on nine image sets demonstrate the advantage of our method. Moreover, the discovered graphlets from each sub-category accurately capture those tiny discriminative object components, e.g., bird claws, heads, and bodies. [ABSTRACT FROM PUBLISHER]

Effective representation of image texture is important for an image-classification task. Statistical modelling in wavelet domains has been widely used to image texture representation. However, due to the intraclass complexity and interclass diversity of textures, it is hard to use a predefined probability distribution function to fit adaptively all wavelet subband coefficients of different textures. In this article, we propose a novel modelling approach, Heterogeneous and Incrementally Generated Histogram (HIGH), to indirectly model the wavelet coefficients by use of four local features in wavelet subbands. By concatenating all the HIGHs in all wavelet subbands of a texture, we can construct a nonnegative multiresolution vector (NMV) to represent a texture image. Considering the NMV’s high dimensionality and nonnegativity, we further propose a Hessian regularized discriminative nonnegative matrix factorization to compute a low-dimensional basis of the linear subspace of NMVs. Finally, we present a texture classification approach by projecting NMVs on the low-dimensional basis. Experimental results show that our proposed texture classification method outperforms seven representative approaches. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel energy optimization framework to accurately estimate surface normal and reflectance of an object from an input image sequence. Input images are captured from a fixed viewpoint under varying lighting conditions. In the proposed approach we combine photometric stereo and Retinex constraints into our energy function. To formulate inter-image constraints, shading information is added to the Lambertian model to account for shadows. For intra-image constraints, we moderate the strength of shading smoothness according to shadow mask and normal variations. By minimizing this energy function we are able to recover accurate surface normals and reflectance. Experimental results show that our approach yields more realistic normal map and accurate albedo map than the state-of-the-art uncalibrated photometric stereo algorithms. As for intrinsic image decomposition, results on the real and synthetic scenes show that the proposed approach outperforms previous ones. [ABSTRACT FROM PUBLISHER]

This paper presents a fast and robust level set method for image segmentation. To enhance the robustness against noise, we embed a Markov random field (MRF) energy function to the conventional level set energy function. This MRF energy function builds the correlation of a pixel with its neighbors and encourages them to fall into the same region. To obtain a fast implementation of the MRF embedded level set model, we explore algebraic multigrid (AMG) and sparse field method (SFM) to increase the time step and decrease the computation domain, respectively. Both AMG and SFM can be conducted in a parallel fashion, which facilitates the processing of our method for big image databases. By comparing the proposed fast and robust level set method with the standard level set method and its popular variants on noisy synthetic images, synthetic aperture radar (SAR) images, medical images, and natural images, we comprehensively demonstrate the new method is robust against various kinds of noises. In particular, the new level set method can segment an image of size $500 \times 500$ within 3 s on MATLAB R2010b installed in a computer with 3.30-GHz CPU and 4-GB memory. [ABSTRACT FROM AUTHOR]

Abstract: Image segmentation is a fundamental problem in computer vision and image analysis. Specially, the segmentation of medical images can assist doctors in making decisions. Due to the lack of distinctive features to describe the boundary of an organ and match function with high performance for features, medical image segmentation is difficult to be achieved with high accuracy. In this paper, an one-class classifier is proposed as the match function to decide whether the pixel belongs to the boundary or not. The proposed method is comprised of two steps. At first, a feature vector space is built with the gradient feature and its statistical information in the training stage. In the test image, a feature vector of one candidate probably being located on the boundary is reconstructed by sparse coding with the feature vector space. After reconstruction, the candidate is classified belonging to boundary or non-boundary via the reconstruction based one-class classifier. Then, in order to maintain the consistency between the candidates which are neighbors to each other, the neighboring candidates are coded using group lasso with the same dictionary. Compared to the traditional methods, the proposed one has three advantages. Firstly, it solves the non-Gaussian distribution problem of the positive samples. Secondly, it avoids large variation among the negative samples. Thirdly, the relationship of the neighboring candidates is considered and used in classification, which is ignored in other methods. The proposed method is validated on 52 MR images of prostate and outperforms Mahalanobis distance, which is considered as one of the state-of-the-art match functions. The experimental results show that the segmentation accuracy can be significantly improved by the proposed method with one-class classification. [Copyright &y& Elsevier]

Abstract: The face almost always has an axis-symmetrical structure. However, as the face usually does not have an absolutely frontal pose when it is imaged, the majority of face images are not symmetrical images. These facts inspire us that the mirror image of the face image might be viewed as a representation of the face with a possible pose opposite to that of the original face image. In this paper we propose a scheme to produce the mirror image of the face and integrate the original face image and its mirror image for representation-based face recognition. This scheme is simple and computationally efficient. Almost all the representation-based classification methods can be improved by this scheme. The underlying rationales of the scheme are as follows: first, the use of the mirror image can somewhat overcome the misalignment problem of the face image in face recognition. Second, it is able to somewhat eliminate the side-effect of the variation of the pose and illumination of the original face image. The experiments show that the proposed scheme can greatly improve the accuracy of the representation-based classification methods. The proposed scheme might be also helpful for improving other face recognition methods. [Copyright &y& Elsevier]

Vision-based power line detection (PLD) is an important yet challenging problem in low-altitude flight. Different from the traditional PLD methods, which only aim at line information, we propose a novel object-aware PLD method to obtain better detection performance. A new definition of power line is first proposed to present its object-aware properties; and then a cascaded PLD scheme is devised with line detection, region filtration, and object validation based on corresponding image cues in joint color (RGB) and near-infrared (NIR) images. Considering that the primary goal of PLD is to capture all potential information and decrease the false negatives, we first treat the universal line shape in pixel from joint RGB-NIR images as a basic feature to explore general line candidates. To further pick out the accurate regions occupied by power lines, on the one hand we filter the false candidates based on the region-based intensity of special material characteristics in NIR, and on the other hand we validate the power lines according to the color features in RGB. The experiments demonstrate the advantages of our proposed method in three aspects: good detection accuracy, high true detection rate, and low false detection rate. [ABSTRACT FROM AUTHOR]

Robust reversible watermarking (RRW) methods are popular in multimedia for protecting copyright, while preserving intactness of host images and providing robustness against unintentional attacks. However, conventional RRW methods are not readily applicable in practice. That is mainly because: 1) they fail to offer satisfactory reversibility on large-scale image datasets; 2) they have limited robustness in extracting watermarks from the watermarked images destroyed by different unintentional attacks; and 3) some of them suffer from extremely poor invisibility for watermarked images. Therefore, it is necessary to have a framework to address these three problems, and further improve its performance. This paper presents a novel pragmatic framework, wavelet-domain statistical quantity histogram shifting and clustering (WSQH-SC). Compared with conventional methods, WSQH-SC ingeniously constructs new watermark embedding and extraction procedures by histogram shifting and clustering, which are important for improving robustness and reducing run-time complexity. Additionally, WSQH-SC includes the property-inspired pixel adjustment to effectively handle overflow and underflow of pixels. This results in satisfactory reversibility and invisibility. Furthermore, to increase its practical applicability, WSQH-SC designs an enhanced pixel-wise masking to balance robustness and invisibility. We perform extensive experiments over natural, medical, and synthetic aperture radar images to show the effectiveness of WSQH-SC by comparing with the histogram rotation-based and histogram distribution constrained methods. [ABSTRACT FROM AUTHOR]

Recently, much attention has been drawn to the problem of matrix completion, which arises in a number of fields, including computer vision, pattern recognition, sensor network, and recommendation systems. This paper proposes a novel algorithm, named robust alternative minimization (RAM), which is based on the constraint of low rank to complete an unknown matrix. The proposed RAM algorithm can effectively reduce the relative reconstruction error of the recovered matrix. It is numerically easier to minimize the objective function and more stable for large-scale matrix completion compared with other existing methods. It is robust and efficient for low-rank matrix completion, and the convergence of the RAM algorithm is also established. Numerical results showed that both the recovery accuracy and running time of the RAM algorithm are competitive with other reported methods. Moreover, the applications of the RAM algorithm to low-rank image recovery demonstrated that it achieves satisfactory performance. [ABSTRACT FROM AUTHOR]

The neighbor-embedding (NE) algorithm for single-image super-resolution (SR) reconstruction assumes that the feature spaces of low-resolution (LR) and high-resolution (HR) patches are locally isometric. However, this is not true for SR because of one-to-many mappings between LR and HR patches. To overcome or at least to reduce the problem for NE-based SR reconstruction, we apply a joint learning technique to train two projection matrices simultaneously and to map the original LR and HR feature spaces onto a unified feature subspace. Subsequently, the k-nearest neighbor selection of the input LR image patches is conducted in the unified feature subspace to estimate the reconstruction weights. To handle a large number of samples, joint learning locally exploits a coupled constraint by linking the LR–HR counterparts together with the K-nearest grouping patch pairs. In order to refine further the initial SR estimate, we impose a global reconstruction constraint on the SR outcome based on the maximum a posteriori framework. Preliminary experiments suggest that the proposed algorithm outperforms NE-related baselines. [ABSTRACT FROM AUTHOR]

Abstract: The proportion of aurora to the field-of-view in temporal series of all-sky images is an important index to investigate the evolvement of aurora. To obtain such an index, a crucial phase is to segment the aurora from the background of sky. A new aurora segmentation approach, including a feature extraction method and the segmentation algorithm, is presented in this paper. The proposed feature extraction method, called adaptive local binary patterns (ALBP), selects the frequently occurred patterns to construct the main pattern set, which avoids using the same pattern set to describe different texture structures in traditional local binary patterns. According to the different morphologies and different semantics of aurora, the segmentation algorithm is designed into two parts, texture part segmentation based on ALBP features and patch part segmentation based on modified Otsu method. As it is simple and efficient, our implementation is suitable for large-scale datasets. The experiments exhibited the segmentation effect of the proposed method is satisfactory from human visual aspect and segmentation accuracy. [Copyright &y& Elsevier]

Eye detection plays an important role in many practical applications. This paper presents a novel two-step scheme for eye detection. The first step models an eye by a newly defined visual-context pattern (VCP), and the second step applies semisupervised boosting for precise detection. VCP describes both the space and appearance relations between an eye region (region of eye) and a reference region (region of reference). The context feature of a VCP is extracted by using the integral image. Aiming to reduce the human labeling efforts, we apply semisupervised boosting, which integrates the context feature and the Haar-like features for precise eye detection. Experimental results on several standard face data sets demonstrate that the proposed approach is effective, robust, and efficient. We finally show that this approach is ready for practical applications. [ABSTRACT FROM AUTHOR]

Abstract: Multi-frame image super-resolution (SR) aims to utilize information from a set of low-resolution (LR) images to compose a high-resolution (HR) one. As it is desirable or essential in many real applications, recent years have witnessed the growing interest in the problem of multi-frame SR reconstruction. This set of algorithms commonly utilizes a linear observation model to construct the relationship between the recorded LR images to the unknown reconstructed HR image estimates. Recently, regularization-based schemes have been demonstrated to be effective because SR reconstruction is actually an ill-posed problem. Working within this promising framework, this paper first proposes two new regularization items, termed as locally adaptive bilateral total variation and consistency of gradients, to keep edges and flat regions, which are implicitly described in LR images, sharp and smooth, respectively. Thereafter, the combination of the proposed regularization items is superior to existing regularization items because it considers both edges and flat regions while existing ones consider only edges. Thorough experimental results show the effectiveness of the new algorithm for SR reconstruction. [Copyright &y& Elsevier]

Image quality is a key characteristic in image processing,10,11 image retrieval,12,13 and biometrics.14 In this paper, a novel reduced-reference image quality assessment method is proposed based on wavelet transform. By simulating the human visual system, we take the variance of the visual sensitive coefficients into account to measure a distorted image. The computational complexity of the proposed method is much lower compared with some existing methods. Experimental results demonstrate its advantages in terms of correlation coefficient, outlier ratio, transmitted information, and CPU cost. Moreover, it is also illustrated that the proposed method has a good accordance with human subjective perception. [ABSTRACT FROM AUTHOR]

Human tastes in art motivate the need for effective means to build a visual mosaic picture which is made up of many small tiles. In some previous work researchers have tried to translate pictures' styles.1 In this paper, a new approach to image processing in arts is presented in the domain of generating a series of artistic mosaic pictures. An arbitrary image is first translated into a mosaic-based one by dividing it into a number of sub-blocks each with the mean value of the pixels in it. Each of these small fragments can be assigned a new location within this image so that a new mosaic picture is generated. By this mean, images with similar color features can be used to create a series of mosaic pictures. The mosaic pictures consist of the same elements as each other, but might be extremely different from the semantic contents. A basic algorithm is presented, followed by some further improvements. Some preliminary experimental results are then given to show the impact of the proposed special techniques. [ABSTRACT FROM AUTHOR]

Abstract: In video segmentation, an intrinsic problem is that the moving cast shadows are always misclassified as part of the moving objects. This paper presents a novel moving cast shadow detection algorithm. The experiments demonstrate shadow region can be removed quite well and thus good video segmentation results can be obtained. [Copyright &y& Elsevier]

Abstract: In this paper, two dimensional principal components of natural images (2D-PCs) are proposed. Similar to principal components of natural images (1D-PCs), 2D-PCs can also be viewed as fundamental components of human''s receptive field because they contain edge-like, bar-like and grating-like patterns. However, compared to 1D-PCs, 2D-PCs are of surprising symmetry, stable regularity, good interpretability, and have little computational complexity in real applications. Then, based on 1D-PCs and 2D-PCs, we design two kinds of statistical texture features (STF(1D) and STF(2D)), and apply them to multi-class facial expression recognition. Numerous experimental results demonstrate that our statistical texture features are better or not worse than other popular features for facial expression recognition. [Copyright &y& Elsevier]

Abstract: While Histograms of Oriented Gradients (HOG) plus Support Vector Machine (SVM) (HOG+SVM) is the most successful human detection algorithm, it is time-consuming. This paper proposes two ways to deal with this problem. One way is to reuse the features in blocks to construct the HOG features for intersecting detection windows. Another way is to utilize sub-cell based interpolation to efficiently compute the HOG features for each block. The combination of the two ways results in significant increase in detecting humans—more than five times better. To evaluate the proposed method, we have established a top-view human database. Experimental results on the top-view database and the well-known INRIA data set have demonstrated the effectiveness and efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

The face is the most distinctive and widely used key to a person's identity. The area of face detection has attracted considerable attention in the advancement of human-machine interaction as it provides a natural and efficient way to communicate between humans and machines. The problem of facial parts in image sequences has become a popular area of research due to emerging applications in intelligent human-computer interface, surveillance systems, content-based image retrieval, video conferencing, financial transaction, forensic applications, pedestrian detection, image database management system and so on. This paper presents the results of an image based neural network face detection system which seeks to address the problem of detecting faces under gross variations. [ABSTRACT FROM AUTHOR]

As one type of local invariant feature, corner feature plays an important role in diverse applications such as: video mining, target detection, image classification, image retrieval, and image matching, etc. However, there are few studies on corner feature for hyperspectral image (HSI). Therefore, this paper proposes a novel corner feature for HSI named extreme-constrained spatial-spectral corner (ECSSC for short) and its corresponding detector. The definition of ECSSC is developed based on the definition of spectral-spatial interest point and the characteristic of HSI. Based on this definition, the detector of ECSSC is put forward and introduced in detail. Then, as an important application of ECSSC, an efficient framework for image-level HSI classification is designed based on ECSSC and parallel computation. The experimental results show that the proposed algorithm can detect abundant corner features with high repeatability rate from HSI and the accuracy of image-level HSI based on ECSSC is dramatically higher than that of the state of the art. [ABSTRACT FROM AUTHOR]

The codebook model has been developed as an effective means for image classification. However, the inherent operation of assigning visual words to image feature vectors in traditional codebook approaches causes serious ambiguities in image classification. In particular, the nearest word may not be the best fit to a feature, and multiple words may be equally appropriate for one specific feature. To resolve these ambiguities, we propose a novel visual codebook model based on the n- dimensional fuzzy geometry ( n -D FG) theory, where all visual words and features are modeled as fuzzy points in the n -D FG space, and appropriate uncertainty is introduced to each fuzzy point to enhance the representation capacity. This n -D FG-codebook model not only inherits advantages from the fuzzy set theory, but also facilitates the analysis and determination of the relationship between visual words and features in geometric form. By explicitly taking into account the ambiguities, we propose a novel measure of similarity between the visual words and fuzzy features. Following the proposed codebook model and the novel similarity measure, we develop two useful image classification algorithms by modifying popular image coding algorithms (i.e. SPM and LLC). Finally, experimental results demonstrate that the classification accuracy of the proposed algorithms is dramatically improved for a standard large-scale image database. For example, with a codebook size of 256, the proposed algorithms achieve similar performance as traditional algorithms with a codebook size of 1024, indicating that the proposed algorithms reduce the computational cost by 75% while achieving almost identical classification accuracy to traditional algorithms. Thus, the proposed algorithms represent a more efficient and appropriate scheme for big image data. [ABSTRACT FROM AUTHOR]

Abstract: Segmentation of medical images is an inevitable image processing step for computer-aided diagnosis. Due to complex acoustic inferences and artifacts, accurate extraction of breast lesions in ultrasound images remains a challenge. Although there have been many segmentation techniques proposed, the performance often varies with different image data, leading to poor adaptability in real applications. Intelligent computing techniques for adaptively learning the boundaries of image objects are preferred. This paper focuses on optimization of a previously documented method called robust graph-based (RGB) segmentation algorithm to extract breast tumors in ultrasound images more adaptively and accurately. A novel technique named as parameter-automatically optimized robust graph-based (PAORGB) image segmentation method is accordingly proposed and performed on breast ultrasound images. A particle swarm optimization algorithm is incorporated with the RGB method to achieve optimal or approximately optimal parameters. Experimental results have shown that the proposed technique can more accurately segment lesions from ultrasound images compared to the RGB and two conventional region-based methods. [Copyright &y& Elsevier]

Abstract: Heterogeneous image transformation (HIT) plays an important role in both law enforcements and digital entertainment. Some available popular transformation methods, like locally linear embedding based, usually generate images with lower definition and blurred details mainly due to two defects: (1) these approaches use a fixed number of nearest neighbors (NN) to model the transformation process, i.e., K-NN-based methods; (2) with overlapping areas averaged, the transformed image is approximately equivalent to be filtered by a low pass filter, which filters the high frequency or detail information. These drawbacks reduce the visual quality and the recognition rate across heterogeneous images. In order to overcome these two disadvantages, a two step framework is constructed based on sparse feature selection (SFS) and support vector regression (SVR). In the proposed model, SFS selects nearest neighbors adaptively based on sparse representation to implement an initial transformation, and subsequently the SVR model is applied to estimate the lost high frequency information or detail information. Finally, by linear superimposing these two parts, the ultimate transformed image is obtained. Extensive experiments on both sketch-photo database and near infrared–visible image database illustrates the effectiveness of the proposed heterogeneous image transformation method. [Copyright &y& Elsevier]

Abstract: Mammographic mass segmentation plays an important role in computer-aided diagnosis systems. It is very challenging because masses are always of low contrast with ambiguous margins, connected with the normal tissues, and of various scales and complex shapes. To effectively detect true boundaries of mass regions, we propose a feature embedded vector-valued contour-based level set method with relaxed shape constraint. In particular, we initially use the contour-based level set method to obtain the initial boundaries on the smoothed mammogram as the shape constraint. To prevent the contour leaking and meanwhile preserve the radiative characteristics of specific malignant masses, afterward, we relax the obtained shape constraint by analyzing possible valid regions around the initial boundaries. The relaxed shape constraint is then used to design a novel stopping function for subsequent vector-valued level set method. Since texture maps, gradient maps, and the original intensity map can reflect different characteristics of the mammogram, we integrate them together to obtain more accurate segmentation by incorporating the new stopping function into the newly proposed feature embedded vector-valued contour-based level set method. The experimental results suggest that the proposed feature embedded vector-valued contour-based level set method with relaxed shape constraint can effectively find ambiguous margins of the mass regions. Comparing against existing active contours methods, the new scheme is more effective and robust in detecting complex masses. [Copyright &y& Elsevier]

Abstract: Face recognition by sketches in photos remains a challenging task. Unlike the existing sketch–photo recognition methods, which convert a photo into sketch and then perform the sketch–photo recognition through sketch–sketch recognition, this paper devotes to synthesizing a photo from the sketch and transforming the sketch–photo recognition to photo–photo recognition to achieve better performance in mixture pattern recognition. The contribution of this paper mainly focuses on two aspects: (1) in view of that there are no many research findings of sketch–photo recognition based on the pseudo-photo synthesis and the existing methods require a large set of training samples, which is nearly impossible to achieve for the high cost of sketch acquisition, we make use of embedded hidden Markov model (EHMM), which can learn the nonlinearity of sketch–photo pair with less training samples, to produce pseudo-photos in terms of sketches; and (2) photos and sketches are divided into patches and pseudo-photo is generated by combining pseudo-photo patches, which makes pseudo-photo more recognizable. Experimental results demonstrate that the newly proposed method is effective to identify face sketches in photo set. [Copyright &y& Elsevier]

Abstract: This paper proposes a simple scene segmentation method based on incremental principal component analysis (IPCA). Instead of segmenting moving objects in a conventional frame by frame manner, the newly proposed method segments a scene into unchanged background zone (UBZ) and moving object zone (MOZ). As a result, moving objects normally appear in MOZs rather than UBZs, and therefore, detection and behaviours analysis can be performed in MOZs. In visual communication, UBZs do not need to be encoded and transmitted. Moreover, if an object is in UBZs, it can be linked to abnormal events. Experimental results demonstrate the contribution of the proposed method. [Copyright &y& Elsevier]

• This paper considers four directions of multi-label learning. • The hierarchical constraint guarantees the hierarchical label connections. • The low-rank constrains guarantees the low-rank property of multi-label projection. • MDML outperforms competitors in effectiveness and efficiency. In multi-label learning, the key problem is to capture the relationships between multiple labels, including proximities and unconformities. In this paper, we consider the relationships among multiple labels from multi-directions, including utilizing discriminative classifier, proposing a general hierarchical constraint and proximity correlation, meanwhile combining low-rank constraint, to infer a novel Multi-Directional Multi-Label learning (MDML) model. To optimize the problems involved in to the proposed models, we develop an iterative algorithms based on the alternating direction method of multipliers (ADMM) algorithm. In the simulations, the experimental results on 4 popular benchmark datasets demonstrate the superiorities of MDML model. [ABSTRACT FROM AUTHOR]