Search

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]

Extracting the foreground from a given complex image is an important and challenging problem. Although there have been many methods to perform foreground extraction, most of them are time-consuming, and the trimaps used in the matting step are labeled manually. In this paper, we propose a fast interactive foreground extraction method based on the superpixel GrabCut and image matting. Specifically, we first extract superpixels from a given image and apply GrabCut on them to obtain a raw mask. Due to that the resulting mask border is hard and toothing, we further propose fast and adaptive trimaps (FATs), and construct an FATs-based shared matting for computing a refined mask. Finally, by interactive processing, we can obtain the final foreground. Experimental results on the BSDS500 and alphamatting datasets demonstrate that our proposed method is faster than five representative methods, and performs better than the interactive representative methods in terms of the three evaluation criteria: 1) mean square error; 2) sum of absolute difference; and 3) execution time. [ABSTRACT FROM AUTHOR]

With fast development of information engineering and social network, people’s locations can be conveniently sensed by spatial technology, such as global positioning systems (GPS), base stations, Wi-Fi access points and even from the appearances of the photos they have taken. The social networks and the online shopping platforms have been gathering billions of users, who share a large amount of images taken in places they live in and visit. We can leverage the social networks to express our opinions about the services and places of interest (POIs). The interactions among users, and user and POIs or services generate big social media data, which have rich information for user, location, and service cognition. Many real-time network applications rely heavily on the accurate social users’ locations. How to sense the locations from multisource social media data is very important and challenging. Thus, in this paper, we give a systematic review of the works that combine social media and spatial technology for POI cognition and image localization. [ABSTRACT FROM PUBLISHER]

Effective parsing of video through the spatial and temporal domains is vital to many computer vision problems because it is helpful to automatically label objects in video instead of manual fashion, which is tedious. Some literatures propose to parse the semantic information on individual 2D images or individual video frames, however, these approaches only take use of the spatial information, ignore the temporal continuity information and fail to consider the relevance of frames. On the other hand, some approaches which only consider the spatial information attempt to propagate labels in the temporal domain for parsing the semantic information of the whole video, yet the non-injective and non-surjective natures can cause the black hole effect. In this paper, inspirited by some annotated image datasets (e.g., Stanford Background Dataset, LabelMe, and SIFT-FLOW), we propose to transfer or propagate such labels from images to videos. The proposed approach consists of three main stages: I) the posterior category probability density function (PDF) is learned by an algorithm which combines frame relevance and label propagation from images. II) the prior contextual constraint PDF on the map of pixel categories through whole video is learned by the Markov Random Fields (MRF). III) finally, based on both learned PDFs, the final parsing results are yielded up to the maximum a posterior (MAP) process which is computed via a very efficient graph-cut based integer optimization algorithm. The experiments show that the black hole effect can be effectively handled by the proposed approach. [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]

Abstract: Image-based power line detection is highly important for threat avoidance when the aerial vehicles fly in low altitude. However, it is very challenging for the requirements of high detection rates, low false alarms and real-time application. In this paper, a sequential local-to-global power line detection algorithm is proposed. In the local criterion, a line segment pool is detected by morphological filtering an edge map image, which is computed based on matched filter (MF) and first-order derivative of Gaussian (FDOG). It results in over detection to guarantee high detection rates. In the next global criterion, grouping the line segments into whole power lines is formulated as a graph-cut model based on graph theory. The principal advantage of the proposed algorithm is that it can detect not only the straight power lines but also the curve ones. Experimental results demonstrate that the algorithm has good performances both in detection accuracy and in processing time. [Copyright &y& Elsevier]

Human segmentation in photo images is a challenging and important problem that finds numerous applications ranging from album making and photo classification to image retrieval. Previous works on human segmentation usually demand a time-consuming training phase for complex shape-matching processes. In this paper, we propose a straightforward framework to automatically recover human bodies from color photos. Employing a coarse-to-fine strategy, we first detect a coarse torso (CT) using the multicue CT detection algorithm and then extract the accurate region of the upper body. Then, an iterative multiple oblique histogram algorithm is presented to accurately recover the lower body based on human kinematics. The performance of our algorithm is evaluated on our own data set (contains 197 images with human body region ground truth data), VOC 2006, and the 2010 data set. Experimental results demonstrate the merits of the proposed method in segmenting a person with various poses. [ABSTRACT FROM AUTHOR]

In this paper, we study the problem of detecting sudden pedestrian crossings to assist drivers in avoiding accidents. This application has two major requirements: to detect crossing pedestrians as early as possible just as they enter the view of the car-mounted camera and to maintain a false alarm rate as low as possible for practical purposes. Although many current sliding-window-based approaches using various features and classification algorithms have been proposed for image-/video-based pedestrian detection, their performance in terms of accuracy and processing speed falls far short of practical application requirements. To address this problem, we propose a three-level coarse-to-fine video-based framework that detects partially visible pedestrians just as they enter the camera view, with low false alarm rate and high speed. The framework is tested on a new collection of high-resolution videos captured from a moving vehicle and yields a performance better than that of state-of-the-art pedestrian detection while running at a frame rate of 55 fps. [ABSTRACT FROM AUTHOR]

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: For image analysis, an important extension to principal component analysis (PCA) is to treat an image as multiple samples, which helps alleviate the small sample size problem. Various schemes of transforming an image to multiple samples have been proposed. Although having been shown effective in practice, the schemes are mainly based on heuristics and experience. In this paper, we propose a probabilistic PCA model, in which we explicitly represent the transformation scheme and incorporate the scheme as a stochastic component of the model. Therefore fitting the model automatically learns the transformation. Moreover, the learned model allows us to distinguish regions that can be well described by the PCA model from those that need further treatment. Experiments on synthetic images and face data sets demonstrate the properties and utility of the proposed model. [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: With the digital all-sky imager (ASI) emergence in aurora research, millions of images are captured annually. However, only a fraction of which can be actually used. To address the problem incurred by low efficient manual processing, an integrated image analysis and retrieval system is developed. For precisely representing aurora image, macroscopic and microscopic features are combined to describe aurora texture. To reduce the feature dimensionality of the huge dataset, a modified local binary pattern (LBP) called ALBP is proposed to depict the microscopic texture, and scale-invariant Gabor and orientation-invariant Gabor are employed to extract the macroscopic texture. A physical property of aurora is inducted as region features to bridge the gap between the low-level visual features and high-level semantic description. The experiments results demonstrate that the ALBP method achieves high classification rate and low computational complexity. The retrieval simulation results show that the developed retrieval system is efficient for huge dataset. [Copyright &y& Elsevier]

Assessing aesthetic appeal of images is a highly subjective task which has attracted a lot of interests recently. It is an interdisciplinary subject related to art, psychology, and computer vision. In this paper, we systematically study prior researches of feature extraction in this area, and category them into four groups, low level, rule based, information theory, and visual attention. In each group, the effectiveness and limitations of existing features are examined. Based on the analysis, we propose a comprehensive feature set, which include 16 novel features and 70 well proved features. With this feature set, we build the system under machine learning scheme consisting of an SVM based classifier to estimate if an image is high aesthetic or low aesthetic . The experiments are conducted on public datasets show that our comprehensive feature set outperforms conventional models that concentrate mainly on certain types of features. The combination of our features produces a promising classification accuracy of 82.4% and a good performance comparable to aesthetic rating of human. Finally, we implemented the proposed evaluation system on mobile devices. It can provide real-time feedback to help users capture appealing photos. [ABSTRACT FROM AUTHOR]

Abstract: Face recognition is one of the biometric identification methods with the highest potential. The existing face recognition algorithms relying on the texture information of face images are affected greatly by the variation of expression, scale and illumination. Whereas the algorithms based on the shape topology weaken the influence of illumination to some extent, but the impact of expression, scale and illumination on face recognition is still unsolved. To this end, we propose a new method for face recognition by integrating texture information with shape information, called biview face recognition algorithm. The texture models are constructed by using subspace learning methods and shape topologies are formed by building graphs for face images. The proposed biview face recognition method is compared with recognition algorithms merely based on texture or shape information. Experimental results of recognizing faces under the variation of illumination, expression and scale demonstrate that the performance of the proposed biview face recognition outperforms texture-based and shape-based algorithms. [Copyright &y& Elsevier]

Abstract: Based on the assumption about the sparse representation of natural images and the theory of compressed sensing, very promising results about single-image super-resolution were obtained by an excellent algorithm introduced by Yang et al. [45]. However, their success could not be well explained theoretically. The lack of theoretical insight has hindered the further improvement of the algorithm. In this paper, Yang’s algorithm is revisited in the view of learning theory. According to this point, Yang’s algorithm can be considered as a linear regression method in a special feature space which is named as sparse coding space by us. In fact, it has been shown that Yang’s algorithm is a result of optimal linear estimation in sparse coding space. More importantly, our theoretical analysis suggests that Yang’s algorithm can be improved by using more flexible regression methods than the linear regression method. Following the idea, a novel single-image super-resolution algorithm which is designed based on the framework of L 2-Boosting is proposed in the paper. The experimental results show the effectiveness of the proposed algorithm by comparing with other methods, which verify our theoretical analysis about Yang’s algorithm. [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: 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]