De Xu

Beijing Jiaotong University, Peping, Beijing, China

Are you De Xu?

Claim your profile

Publications (88)6.88 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: Combinatorial maps are widely used in image representation and processing, however map matching problems have not been extensively researched. This paper addresses the problem of inexact matching between labeled combinatorial maps. First, the concept of edit distance is extended to combinatorial maps, and then used to define mapping between combinatorial maps as a sequence of edit operations that transforms one map into another. Subsequently, an optimal approach based on A* algorithm and an approximate approach based on Greedy algorithm are proposed to compute the distance between combinatorial maps. Experimental results show that the proposed inexact map matching approach produces richer search results than the exact map matching technique by tolerating small difference between maps. The proposed approach performs better in practice than the previous approach based on maximum common submap which cannot be directly used for comparing labels on the maps.
    Computer Vision and Image Understanding 12/2012; 116(12):1168–1177. · 1.23 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    IEICE Transactions on Information and Systems 01/2012; E95.D(5):1556-1559. · 0.22 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We define WordNet based hierarchy concept tree (HCT) and hierarchy concept graph (HCG), HCT contains hyponym/hypernym kind of relation in WordNet while HCG has more meronym/holonym kind of edges than in HCT, and present an advanced concept vector model for generalizing standard representations of concept similarity in terms of WordNet-based HCT. In this model, each concept node in the hierarchical tree has ancestor and descendent concept nodes composing its relevancy nodes, thus a concept node is represented as a concept vector according to its relevancy nodes’ local density and the similarity of the two concepts is obtained by computing the cosine similarity of their vectors. In addition, the model is adjustable in terms of multiple descendent concept nodes. This paper also provides a method by which this concept vector may be applied with regard to HCG into HCT. With this model, semantic similarity and relatedness are computed based on HCT and HCG. The model contains structural information inherent to and hidden in the HCT and HCG. Our experiments showed that this model compares favorably to others and is flexible in that it can make comparisons between any two concepts in a WordNet-like structure without relying on any additional dictionary or corpus information.
    Journal of Systems and Software. 01/2012; 85:370-381.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Removing shadows from single color images is an important problem in computer vision. In this paper, we propose a novel shadow removal approach, which could effectively remove shadows from textured surfaces, yielding high quality shadow-free images. Our approach aims at calculating scale factors to cancel the effect of shadows. Based on the regional gray edge hypothesis, which assumes the average of the reflectance differences in a region is achromatic, the scale factors can be computed without the restrictions that former algorithms need. The experimental results show that the proposed algorithm is effective.
    Optical Engineering 12/2011; 50(12):7001-. · 0.88 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Scene Categorization with Classified Codebook Model
    IEICE Transactions. 01/2011; 94-D:1349-1352.
  • J. Inf. Sci. Eng. 01/2011; 27:197-211.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Combinatorial maps explicitly encode orientations of edges around vertices, and have been used in many fields. In this paper, we address the problem of searching for patterns in model maps by putting forward the concept of symbol graph. A symbol graph will be constructed and stored for each model map in the preprocessing. Furthermore, an algorithm for submap isomorphism is presented based on symbol sequence searching in the symbol graphs. The computational complexity of this algorithm is quadratic in the worst case if we neglect the preprocessing step.
    Pattern Recognition Letters. 01/2011; 32:1100-1107.
  • [Show abstract] [Hide abstract]
    ABSTRACT: A Novel Saliency-Based Graph Learning Framework with Application to CBIR
    IEICE Transactions. 01/2011; 94-D:1353-1356.
  • [Show abstract] [Hide abstract]
    ABSTRACT: One possible solution to estimating the illumination for color constancy and white balance in video sequences would be to apply one of the many existing illumination-estimation algorithms independently to each video frame. However, the frames in a video are generally highly correlated, so we propose a video-based illumination-estimation algorithm that takes advantage of the related information between adjacent frames. The main idea of the method is to cut the video clip into different ‘scenes.’ Assuming all the frames in one scene are under the same (or similar) illuminant, we combine the information from them to calculate the chromaticity of the scene illumination. The experimental results showed that the proposed method is effective and outperforms the original single-frame methods on which it is based.
    Computational Color Imaging - Third International Workshop, CCIW 2011, Milan, Italy, April 20-21, 2011. Proceedings; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: Removing shadows in color images is an important research problem in computer vision. In this paper, we propose a novel shadow removal approach, which effectively removes shadows from textured surfaces, yielding high quality shadow-free images. Our approach aims at calculating scale factors to cancel the effect of shadows. Based on the regional gray edge hypothesis, which assumes the average of the reflectance differences in a region is achromatic, the scale factors can be computed without the restrictions that former algorithms need. The experimental results show that the proposed algorithm is effective and improves the performance of former scale-based shadow removal methods.
    01/2011;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Multi-Scale Multi-Level Generative Model in Scene Classification
    Ieice Transactions - IEICE. 01/2011;
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a method for scene categorization by integrating region contextual information into the popular Bag-of-Visual-Words approach. The Bag-of-Visual-Words approach describes an image as a bag of discrete visual words, where the frequency distributions of these words are used for image categorization. However, the traditional visual words suffer from the problem when faced these patches with similar appearances but distinct semantic concepts. The drawback stems from the independently construction each visual word. This paper introduces Region-Conditional Random Fields model to learn each visual word depending on the rest of the visual words in the same region. Comparison with the traditional Conditional Random Fields model, there are two areas of novelty. First, the initial label of each patch is automatically defined based on its visual feature rather than manually labeling with semantic labels. Furthermore, the novel potential function is built under the region contextual constraint. The experimental results on the three well-known datasets show that Region Contextual Visual Words indeed improves categorization performance compared to traditional visual words.
    Expert Syst. Appl. 01/2011; 38:11591-11597.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Tag ranking has emerged as an important research topic recently due to its potential application on web image search. Existing tag relevance ranking approaches mainly rank the tags according to their relevance levels with respect to a given image. Nonetheless, such algorithms heavily rely on the large-scale image dataset and the proper similarity measurement to retrieve semantic relevant images with multi-labels. In contrast to the existing tag relevance ranking algorithms, in this paper, we propose a novel tag saliency ranking scheme, which aims to automatically rank the tags associated with a given image according to their saliency to the image content. To this end, this paper presents an integrated framework for tag saliency ranking, which combines both visual attention model and multi-instance learning to investigate the saliency ranking order information of tags with respect to the given image. Specifically, tags annotated on the image-level are propagated to the region-level via an efficient multi-instance learning algorithm firstly; then, visual attention model is employed to measure the importance of regions in the given image. Finally, tags are ranked according to the saliency values of the corresponding regions. Experiments conducted on the COREL and MSRC image datasets demonstrate the effectiveness and efficiency of the proposed framework.
    Neurocomputing. 01/2011; 74:3619-3627.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Traditional Chinese painting is a unique form of art and highly regarded for its theory, expression and techniques throughout the world. A traditional Chinese painting is composed of three parts: the mainbody part, the seals part and scripts part. These three parts have many semantics. So extraction of them is important and urgent task. However, popular image processing techniques have little been used in this specific domain. In this paper, a novel algorithm for extraction the scripts part of traditional Chinese painting images is proposed, including the motivations of the algorithm, the description of the algorithm, experiment results and its analysis. This algorithm is mainly based on color and structure feature of Chinese characters in the scripts part of traditional Chinese painting images. The algorithm is simple but has satisfactory efficiency.
    Software Technology and Engineering (ICSTE), 2010 2nd International Conference on; 11/2010
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Although a number of elaborate color constancy algorithms have been proposed, methods such as Grey World and Max-RGB are still widely used because of their low computational costs. The Grey World algorithm is based on the grey world assumption: the average reflectance in a scene is achromatic. But this assumption cannot be always satisfied well. Borrowing on some of the strengths and simplicity of the Grey World algorithm, W. Xiong et al. proposed an advanced illumination estimation method, named Grey Surface Identification (GSI), which identifies those grey surfaces no matter what the light color is and averages them in RGB space. However, this method is camera-dependent, so it cannot be applied on the images from unknown imaging device. Motivated by the paradigm of the GSI, we present a novel iteration method to identify achromatic surface for illumination estimation. Furthermore, the local Grey Edge method is introduced to optimize the initial condition of the iteration so as to improve the accuracy of the proposed algorithm. The experiment results on different image datasets show that our algorithm is effective and outperforms some current state-of-the-art color constancy algorithms. © 2010 Wiley Periodicals, Inc. Col Res Appl, 2010
    Color Research & Application 07/2010; 35(4):304 - 312. · 1.01 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    IEICE Transactions. 01/2010; 93-D:1580-1588.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Keyword query is an important means to find object information in XML document. Most of the existing keyword query approaches adopt the subtrees rooted at the smallest lowest common ancestors of the keyword matching nodes as the basic result units. The structural relationships among XML nodes are excessively emphasized but the semantic relevance is not fully exploited.To change this situation, we propose the concept of entity subtree and emphasis the semantic relevance among different nodes as querying information from XML. In our approach, keyword query cases are improved to a new keyword-based query language, Grouping and Categorization Keyword Expression (GCKE) and the core query algorithm, finding entity subtrees (FEST) is proposed to return high quality results by fully using the keyword semantic meanings exposed by GCKE. We demonstrate the effectiveness and the efficiency of our approach through extensive experiments.
    Journal of Systems and Software. 01/2010; 83:990-1003.
  • Songhe Feng, De Xu
    [Show abstract] [Hide abstract]
    ABSTRACT: Automatic image annotation has emerged as an important research topic due to its potential application on both image understanding and web image search. Due to the inherent ambiguity of image-label mapping and the scarcity of training examples, the annotation task has become a challenge to systematically develop robust annotation models with better performance. From the perspective of machine learning, the annotation task fits both multi-instance and multi-label learning framework due to the fact that an image is usually described by multiple semantic labels (keywords) and these labels are often highly related to respective regions rather than the entire image. In this paper, we propose an improved Transductive Multi-Instance Multi-Label (TMIML) learning framework, which aims at taking full advantage of both labeled and unlabeled data to address the annotation problem. The experiments over the well known Corel 5000 data set demonstrate that the proposed method is beneficial in the image annotation task and outperforms most existing image annotation algorithms.
    Expert Systems with Applications. 01/2010;
  • [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    IEICE Transactions. 01/2010; 93-D:1991-1994.
  • Source
    J. Inf. Sci. Eng. 01/2010; 26:2075-2091.

Publication Stats

131 Citations
6.88 Total Impact Points

Institutions

  • 2004–2012
    • Beijing Jiaotong University
      • School of Computer and Information Technology
      Peping, Beijing, China
  • 2009
    • Northeast Institute of Geography and Agroecology
      • National Pattern Recognition Laboratory
      Beijing, Beijing Shi, China
  • 2005
    • Beijing Union University
      Peping, Beijing, China