Yueheng Sun

Tianjin University, T’ien-ching-shih, Tianjin Shi, China

Are you Yueheng Sun?

Claim your profile

Publications (9)0 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: The key to identifying the packaged grain is the shape of package, and the key to identifying shape is processing and describing the boundary of package. Based on a lot of analysis and experiment, this article select the canny operator and chain code to process and describe the boundary of package. Aiming at the boundary is not absolute connectivity, the closure operation of Mathematical Morphology is introduced to do pretreatment on binary image of packaged grain. Finally the boundary is absolute connectivity. Experiments show that the proposed method enhances the anti-jamming and robustness of edge detection.
    12/2009: pages 1105-1114;
  • Ying Lin, Yang Fu, Yueheng Sun, Yanghong Sun
    [Show abstract] [Hide abstract]
    ABSTRACT: A Fortify method of moving object detection is proposed in this paper. Based on color and edge geometric features, the new method can automatically organize a supervised area. First, by the color features in a real supervised scene, the method extracts several regions of interest (ROI) with noise, then matches them with geometric shape by Fourier descriptors in the database and sequentially achieves an automatic-organizing supervised area. Experimental results show that this method has low operation cost, high efficiency, strong anti-jamming, high accuracy and robustness.
    12/2009: pages 1135-1143;
  • Ying Lin, Yong Liu, Yueheng Sun, Yanhong Sun
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a quantity intelligent reckoning approach for packaged granary grain based on image processing. The actual scene video was taken as the analysis object, and the dual-threshold Canny operator and the morphology processing method are used to extract the object grain bags’ characteristic outline-- the boundary of the counter-band of light. Then, a counting algorithm which integrates mode theory and variance analysis technology is presented for the quantity second-judgment. Experimental results show that by accurately extracting the characteristic outline and counting the number of the characteristic outline, the algorithm presents an effective method for grain quantity detection with high recognition precision and efficiency.
    06/2009: pages 1115-1123;
  • Ying Lin, Liang Ge, Yueheng Sun
    [Show abstract] [Hide abstract]
    ABSTRACT: Because of the traditional methods of video error checking are unfitted to the network environment in which the packet loss rate frequently changes, this paper proposes an adaptive error checking solution on the basis of estimation of the change trend of packet-loss rate. By setting the threshold value of packet-loss rate, the solution takes advantage of improved auto repeat request supported by RDP to realize real-time transportation in a low packet-loss rate, and uses improved forward error correction, a method of dynamically decollating images at the basis of varying sending rate, to solve the problem of error checking in a low transmitting rate.
    06/2009: pages 1125-1134;
  • Yueheng Sun, Weijie Ni, Rui Men
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes an automatic expansion approach for an existing domain-specific dictionary based on web mining. Using the terminology pairs in a dictionary as queries, we first extract snippet fragments that potentially contain the Chinese translations of current English phrases. Based on matching patterns extracted from the Web, we can get the most likely translation for a new English phrase. Finally we use the Vector Space Model to filter out the translation equivalents belong to our expected domain, and a domain-specific dictionary expanded by these new terminology pairs is thereby built. The performance of our approach is verified on a dictionary of finance and accounting, and a precision between 85-90% is achieved on considering different thresholds.
  • Yueheng Sun, Weijie Ni, Rui Men
    [Show abstract] [Hide abstract]
    ABSTRACT: In this article a personalized paper recommendation approach based on the reviewer's interest model is presented in order to increase the number of reviews for online papers. To achieve this purpose, we first model the reviewer's interest based on some useful data extracted from the papers in a journal database, such as titles, abstracts, keywords and the Chinese Library Classification Codes (CLCCs). According to the reviewer's interest model, we then propose a recommendation approach, which can send a paper published online to the reviewers that are experts in the scoop of the paper. Experimental results show that our recommendation approach is effective and achieves 80-90% accuracy in terms of recommending different kinds of papers to the right reviewers.
  • Yueheng Sun, Rui Men, Weijie Ni
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an approach for acquiring academic bilingual resources from the web paper libraries. By analyzing the structured information of web pages, we first implement a customized crawler to download these pages including paper details, and then use a parser to transfer them into XML format. Based on the classic statistical method for sentence alignment, we propose an improved approach to align the initial bilingual resources, in which two factors, bilingual keyword pairs and matching patterns are introduced. Experimental results show that our sentence aligner supported by the new approach achieves performance enhancement by 7% in both precision and recall.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Online forums contain a huge amount of valuable user gener- ated content. In this paper we address the problem of extract- ing question-answer pairs from forums. Question-answer pairs extracted from forums can be used to help Question Answering services (e.g. Yahoo! Answers) among other applications. We propose a sequential patterns based classification method to detect questions in a forum thread, and a graph based propagation method to detect answers for questions in the same thread. Experimental results show that our techniques are very promising. Categories and Subject Descriptors: H.3.3 (Information Search and Retrieval): Retrieval models; I.2.7 (Artificial Intelligence): Natural Language Processing General Terms: Algorithms, Experimentation
    Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008, Singapore, July 20-24, 2008; 01/2008
  • Ying Lin, Yong Liu, Yueheng Sun, Yanhong Sun
    [Show abstract] [Hide abstract]
    ABSTRACT: A scheme for packaged granary grain quantity intelligent reckoning based on image processing was proposed in this paper. According to the actual scene, the grain bag characteristic outline -- the boundary of the counter-band of light was presented and taken as the analysis object. An algorithm combining Canny operator with image morphological thinning are used to extract the outline. Then, a counting algorithm which integrates mode theory and variance analysis technology is presented for the quantity second-judgment. The experimental results indicate that by accurately extracting the characteristic outline and counting the number of the characteristic outline, the algorithm presents an effective method for grain quantity detection with high recognition precision and efficiency.
    2008 International Symposium on Computer Science and Computational Technology, ISCSCT 2008, 20-22 December 2008, Shanghai, China, 2 Volumes; 01/2008