Springer Science and Business Media LLC

We present a supervised learning approach for object-category specific restoration, recognition, and segmentation of images which are blurred using an unknown kernel. The novelty of this work is a multilayer graphical model which unifies the low-level vision task of restoration and the high-level vision task of recognition in a cooperative framework. The graphical model is an interconnected two-layer Markov random field. The restoration layer accounts for the compatibility between sharp and blurred images and models the association between adjacent patches in the sharp image. The recognition layer encodes the entity class and its location in the underlying scene. The potentials are represented using nonparametric kernel densities and are learnt from training data. Inference is performed using nonparametric belief propagation. Experiments demonstrate the effectiveness of our model for the restoration and recognition of blurred license plates as well as face images.

On the basis of analyzing, receiving, and parsing the computer video electromagnetic leakage emission signal, an image of the screen display content can be obtained. Due to the interference noise existing in the receiving process, the received image information may be drifted, the recognition may be poor, and the definition might be low. In order to improve the recognizability of the restored image, firstly, based on image noise analysis, cumulative averaging and noise smoothing, this paper proposes an image processing method based on ambiguity for electromagnetic leakage emission reduction image. Secondly, according to image denoising implementation steps, combined with computer video reproduction example, the image processing method was verified by comprehensive experiments. Lastly, the image evaluation and signal-to-noise ratio analysis of the experimental results were carried out. The results show that the image processing method based on the ambiguity of electromagnetic leakage emission reduction image has some improvement in subjective and objective evaluation with obvious promotion.

This paper presents a robust and adaptable facial feature extraction system used for facial expression recognition in human-computer interaction (HCI) environments. Such environments are usually uncontrolled in terms of lighting and color quality, as well as human expressivity and movement; as a result, using a single feature extraction technique may fail in some parts of a video sequence, while performing well in others. The proposed system is based on a multicue feature extraction and fusion technique, which provides MPEG-4-compatible features assorted with a confidence measure. This confidence measure is used to pinpoint cases where detection of individual features may be wrong and reduce their contribution to the training phase or their importance in deducing the observed facial expression, while the fusion process ensures that the final result regarding the features will be based on the extraction technique that performed better given the particular lighting or color conditions. Real data and results are presented, involving both extreme and intermediate expression/emotional states, obtained within the sensitive artificial listener HCI environment that was generated in the framework of related European projects.

This paper presents a robust computational framework for monocular 3D tracking of human movement. The main innovation of the proposed framework is to explore the underlying data structures of the body silhouette and pose spaces by constructing low-dimensional silhouettes and poses manifolds, establishing intermanifold mappings, and performing tracking in such manifolds using a particle filter. In addition, a novel vectorized silhouette descriptor is introduced to achieve low-dimensional, noise-resilient silhouette representation. The proposed articulated motion tracker is view-independent, self-initializing, and capable of maintaining multiple kinematic trajectories. By using the learned mapping from the silhouette manifold to the pose manifold, particle sampling is informed by the current image observation, resulting in improved sample efficiency. Decent tracking results have been obtained using synthetic and real videos.

The goal of contrast enhancement is to improve visibility of image details without introducing unrealistic visual appearances and/or unwanted artefacts. While global contrast-enhancement techniques enhance the overall contrast, their dependences on the global content of the image limit their ability to enhance local details. They also result in significant change in image brightness and introduce saturation artefacts. Local enhancement methods, on the other hand, improve image details but can produce block discontinuities, noise amplification and unnatural image modifications. To remedy these shortcomings, this article presents a fusion-based contrast-enhancement technique which integrates information to overcome the limitations of different contrast-enhancement algorithms. The proposed method balances the requirement of local and global contrast enhancements and a faithful representation of the original image appearance, an objective that is difficult to achieve using traditional enhancement methods. Fusion is performed in a multi-resolution fashion using Laplacian pyramid decomposition to account for the multi-channel properties of the human visual system. For this purpose, metrics are defined for contrast, image brightness and saturation. The performance of the proposed method is evaluated using visual assessment and quantitative measures for contrast, luminance and saturation. The results show the efficiency of the method in enhancing details without affecting the colour balance or introducing saturation artefacts and illustrate the usefulness of fusion techniques for image enhancement applications.

This paper introduces triangular wavelets, which are two-dimensional nonseparable biorthogonal wavelets defined on the regular triangular lattice. The construction that we propose is a simple nonseparable extension of one-dimensional interpolating wavelets followed by a straightforward generalization. The resulting three oriented high-pass filters are symmetrically arranged on the lattice, while low-pass filters have hexagonal symmetry, thereby allowing an isotropic image processing in the sense that three detail components are distributed uniformly. Applying the triangular filter to images, we explore applications that truly benefit from the triangular wavelets in comparison with the conventional tensor product transforms.

We address the problem of unsupervised discovery of action classes in video data. Different from all existing methods thus far proposed for this task, we present a space-time link analysis approach which consistently matches or exceeds the performance of traditional unsupervised action categorization methods in various datasets. Our method is inspired by the recent success of link analysis techniques in the image domain. By applying these techniques in the space-time domain, we are able to naturally take into account the spatiotemporal relationships between the video features, while leveraging the power of graph matching for action classification. We present a comprehensive set of experiments demonstrating that our approach is capable of handling cluttered backgrounds, activities with subtle movements, and video data from moving cameras. State-of-the-art results are reported on standard datasets. We also demonstrate our method in a compelling surveillance application with the goal of avoiding fraud in retail stores.