Modeling visual attention provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to the modeling bottom-up visual attention. The main contributions are twofold: 1) We use a principal component analysis (PCA) to transform the RGB color space into three principal components, which intrinsically leads to an opponent representation of colors to ensure good saliency analysis. 2) A practicable framework for modeling visual attention is presented based on a region-level reliability analysis for each feature map. And then the salient map can be robustly generated for a variety of nature images. Experiments show that the proposed algorithm is effective and can characterize the human perception well.

Grey world algorithm is a well-known color constancy algorithm. It is based on the Grey-World assumption i.e., the average reflectance of surfaces in the world is achromatic. This algorithm is simple and has low computational costs. However, for the images with several colors, the light source color could not be estimated correctly using the Grey World algorithm. In this paper, we propose a Multi-scale Adaptive Grey World algorithm (MAGW). First, multi-scale images are obtained based on wavelet transformation and the illumination color is estimated from different scales images. Then according to the estimated illumination color, the original image is mapped into the image under a canonical illumination with supervision of an adaptive reliability function, which is based on the image entropy. The experimental results show that our algorithm is effective and also has low computational costs.

We present a novel model, named Category Constraint-Latent Dirichlet Allocation (CC-LDA), to learn and recognize natural scene category. Previous work had to resort to additional classifier after obtaining image topic representation. Our model puts the category information in topic inference, so every category is represented in a different topics simplex and topic size, which is consistent with human cognitive habit. The significant feature in our model is that it can do discrimination without combined additional classifier, during the same time of getting topic representation. We investigate the classification performance with variable scene category tasks. The experiments have demonstrated that our learning model can get better performance with less training data.

The frequency response of log-Gabor function matches well the frequency response of primate visual neurons. In this letter, motion-salient regions are extracted based on the 2D log-Gabor wavelet transform of the spatio-temporal form of actions. A supervised classification technique is then used to classify the actions. The proposed method is robust to the irregular segmentation of actors. Moreover, the 2D log-Gabor wavelet permits more compact representation of actions than the recent neurobiological models using Gabor wavelet.

The manifold-ranking algorithm has been successfully adopted in content-based image retrieval (CBIR) in recent years. However, while the global low-level features are widely utilized in current systems, region-based features have received little attention. In this paper, a novel attention-driven transductive framework based on a hierarchical graph representation is proposed for region-based image retrieval (RBIR). This approach can be characterized by two key properties: (1) Since the issue about region significance is the key problem in region-based retrieval, a visual attention model is chosen here to measure the regions' significance. (2) A hierarchical graph representation which combines region-level with image-level similarities is utilized for the manifold-ranking method. A novel propagation energy function is defined which takes both low-level visual features and regional significance into consideration. Experimental results demonstrate that the proposed approach shows the satisfactory retrieval performance compared to the global-based and the block-based manifold-ranking methods.

Visually saliency detection provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. One of the main aims of visual attention in computer vision is to detect and segment the salient regions in an image. In this paper, we employ matrix decomposition to detect salient object in nature images. To efficiently eliminate high contrast noise regions in the background, we integrate global context information into saliency detection. Therefore, the most salient region can be easily selected as the one which is globally most isolated. The proposed approach intrinsically provides an alternative methodology to model attention with low implementation complexity. Experiments show that our approach achieves much better performance than that from the existing state-of-art methods.

Visual inpainting is an interpolation problem that restores an image or a frame with missing or damaged parts. Over the past decades, a number of computable models of visual inpainting have been developed, but most of these models are based on the pixel domain. Little theoretical and computational work of visual inpainting is based on the compressed domain. In this paper, a visual inpainting model in the discrete cosine transform (DCT) domain is proposed. DCT coefficients of the non-inpainting blocks are utilized to get block features, and those block features are propagated to the inpainting region iteratively. The experimental results with I frames of MPEG4 are presented to demonstrate the efficiency and accuracy of the proposed algorithm.

Color constancy is the ability to measure colors of objects independent of the light source color. Various methods have been proposed to handle this problem. Most of them depend on the statistical distributions of the pixel values. Recent studies show that incorporation image derivatives are more effective than the direct use of pixel values. Based on this idea, a novel edge-based color constancy algorithm using support vector regression (SVR) is proposed. Contrary to existing SVR color constancy algorithm, which is computed from the zero-order structure of images, our method is based on the higher-order structure of images. The experimental results show that our algorithm is more effective than the zero-order SVR color constancy methods.

Localized content-based image retrieval (LCBIR) has emerged as a hot topic more recently because in the scenario of CBIR, the user is interested in a portion of the image and the rest of the image is irrelevant. In this paper, we propose a novel region-level relevance feedback method to solve the LCBIR problem. Firstly, the visual attention model is employed to measure the regional saliency of each image in the feedback image set provided by the user. Secondly, the regions in the image set are constructed to form an affinity matrix and a novel propagation energy function is defined which takes both low-level visual features and regional significance into consideration. After the iteration, regions in the positive images with high confident scores are selected as the candidate query set to conduct the next-round retrieval task until the retrieval results are satisfactory. Experimental results conducted on the SIVAL dataset demonstrate the effectiveness of the proposed approach.

Previous works show that the probabilistic Latent Semantic Analysis (pLSA) model is one of the best generative models for scene categorization and can obtain an acceptable classification accuracy. However, this method uses a certain number of topics to construct the final image representation. In such a way, it restricts the image description to one level of visual detail and cannot generate a higher accuracy rate. In order to solve this problem, we propose a novel generative model, which is referred to as multi-scale multi-level probabilistic Latent Semantic Analysis model (msml-pLSA). This method consists of two parts: multi-scale part, which extracts visual details from the image of diverse resolutions, and multi-level part, which concentrates multiple levels of topic representation to model scene. The msml-pLSA model allows for the description of fine and coarse local image detail in one framework. The proposed method is evaluated on the well-known scene classification dataset with 15 scene categories, and experimental results show that the proposed msml-pLSA model can improve the classification accuracy compared with the typical classification methods.

This paper proposes the Extended Bag-of-Visterms (EBOV) to represent semantic scenes. In previous methods, most representations are bag-of-visterms (BOV), where visterms referred to the quantized local texture information. Our new representation is built by introducing global texture information to extend standard bag-of-visterms. In particular we apply the adaptive weight to fuse the local and global information together in order to provide a better visterm representation. Given these representations, scene classification can be performed by pLSA (probabilistic Latent Semantic Analysis) model. The experiment results show that the appropriate use of global information improves the performance of scene classification, as compared with BOV representation that only takes the local information into account.

This letter proposes a neurobiological approach for action recognition. In this approach, actions are represented by a visual-neuron feature (VNF) based on a quantitative model of object representation in the primate visual cortex. A supervised classification technique is then used to classify the actions. The proposed VNF is invariant to affine translation and scaling of moving objects while maintaining action specificity. Moreover, it is robust to the deformation of actors. Experiments on publicly available action datasets demonstrate the proposed approach outperforms conventional action recognition models based on computer-vision features.

None of the existing color constancy algorithms can be considered universal. Furthermore, they use all the image pixels, although actually not all of the pixels are effective in illumination estimation. Consequently, how to select a proper color constancy algorithm from existing algorithms and how to select effective(or useful) pixels from an image are two most important problems for natural images color constancy. In this paper, a novel Color Constancy method using Effective Regions (CCER) is proposed, which consists of the proper algorithm selection and effective regions selection. For a given image, the most proper algorithm is selected according to its Weilbull distribution while its effective regions are chosen based on image similarity. The experiments show promising results compared with the state-of-the-art methods.

Salient Region Extraction provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to extracting the salient region based on bottom-up visual attention. The main contributions are twofold: 1) Instead of the feature parallel integration, the proposed saliencies are derived by serial processing between texture and color features. Hence, the proposed approach intrinsically provides an alternative methodology to model attention with low implementation complexity. 2) A constructive approach is proposed for rendering an image by a non-linear intensity mapping, which can efficiently eliminate high contrast noise regions in the image. And then the salient map can be robustly generated for a variety of nature images. Experiments show that the proposed algorithm is effective and can characterize the human perception well.

This paper discusses the issues involved in the design of a complete information retrieval system for DataSpace based on user relevance probabilistic schemes. First, Information Hidden Model (IHM) is constructed taking into account the users' perception of similarity between documents. The system accumulates feedback from the users and employs it to construct user oriented clusters. IHM allows integrating uncertainty over multiple, interdependent classifications and collectively determines the most likely global assignment. Second, Three different learning strategies are proposed, namely query-related UHH, UHB and UHS (User Hidden Habit, User Hidden Background, and User Hidden keyword Semantics) to closely represent the user mind. Finally, the probability ranking principle shows that optimum retrieval quality can be achieved under certain assumptions. An optimization algorithm to improve the effectiveness of the probabilistic process is developed. We first predict the data sources where the query results could be found. Therefor, compared with existing approaches, our precision of retrieval is better and do not depend on the size and the DataSpace heterogeneity.

This paper focuses on the relationship between the number of interest points and the accuracy rate in scene classification. Here, we accept the common belief that more interest points can generate higher accuracy. But, few effort have been done in this field. In order to validate this viewpoint, in our paper, extensive experiments based on bag of words method are implemented. In particular, three different SIFT descriptors and five feature selection methods are adopted to change the number of interest points. As innovation point, we propose a novel dense SIFT descriptor named Octave Dense SIFT, which can generate more interest points and higher accuracy, and a new feature selection method called number mutual information (NMI), which has better robustness than other feature selection methods. Experimental results show that the number of interest points can aggressively affect classification accuracy.

In this paper, we present a Double-Anchoring Based Tone Mapping (DABTM) algorithm for displaying high dynamic range (HDR) images. First, two anchoring values are obtained using the double-anchoring theory. Second, we use the two values to formulate the compressing operator, which can achieve the aim of tone mapping directly. A new method based on accelerated K-means for the decomposition of HDR images into groups (frameworks) is proposed. Most importantly, a group of piecewise-overlap linear functions is put forward to define the belongingness of pixels to their locating frameworks. Experiments show that our algorithm is capable of achieving dynamic range compression, while preserving fine details and avoiding common artifacts such as gradient reversals, halos, or loss of local contrast.

Bag-of-Visual-Words representation has recently become popular for scene classification. However, learning the visual words in an unsupervised manner suffers from the problem when faced these patches with similar appearances corresponding to distinct semantic concepts. This paper proposes a novel supervised learning framework, which aims at taking full advantage of label information to address the problem. Specifically, the Gaussian Mixture Modeling (GMM) is firstly applied to obtain "semantic interpretation" of patches using scene labels. Each scene induces a probability density on the low-level visual features space, and patches are represented as vectors of posterior scene semantic concepts probabilities. And then the Information Bottleneck (IB) algorithm is introduce to cluster the patches into "visual words" via a supervised manner, from the perspective of semantic interpretations. Such operation can maximize the semantic information of the visual words. Once obtained the visual words, the appearing frequency of the corresponding visual words in a given image forms a histogram, which can be subsequently used in the scene categorization task via the Support Vector Machine (SVM) classifier. Experiments on a challenging dataset show that the proposed visual words better perform scene classification task than most existing methods.

This paper presents an efficient yet powerful codebook model, named classified codebook model, to categorize natural scene category. The current codebook model typically resorts to large codebook to obtain higher performance for scene categorization, which severely limits the practical applicability of the model. Our model formulates the codebook model with the theory of vector quantization, and thus uses the famous technique of classified vector quantization for scene-category modeling. The significant feature in our model is that it is beneficial for scene categorization, especially at small codebook size, while saving much computation complexity for quantization. We evaluate the proposed model on a well-known challenging scene dataset: 15 Natural Scenes. The experiments have demonstrated that our model can decrease the computation time for codebook generation. What is more, our model can get better performance for scene categorization, and the gain of performance becomes more pronounced at small codebook size.

Computational color constancy is a classical problem in computer vision. It is an under-constrained problem, which can be solved based on some constraint. Existing algorithms can be divided into two groups: physics-based algorithms and statistics-based approaches. In this paper, we propose a new hypothesis that the images generated under a same illumination have some similar features. Based on this hypothesis, a novel statistics-based color constancy algorithm is given and a new similarity function between images is also defined. The experimental results show that our algorithm is effective and it is more important that the dimension of the features in our algorithm is much lower than many former statistics-based algorithms.