최대 빈도수 기반 정규화 체인코드의 특징벡터

다국어 초록 (Multilingual Abstract)

The chain code is extensively used for extracting the feature vector in object recognition or image retrieval. It is used to extract the feature vector because the algorithm is not only simple but also includes the contour information. But as the traditional chain code is very sensitive at the transfer/rotation/scaling of the object, it is very difficult to get the efficient result of the recall or the precision. In this paper, we have proposed a novel algorithm that the feature vectors, which is based on the voting numbers of the rearranged chain code, is extracted. The process is as follows. The object contour based chain code is obtained and rearranged and normalized according to the maximum voting number. After round off, The voting value based chain code is used as the feature vector. By using the MPEG-7 database, the proposed method experimented. It could confirm the robustness for the movement of the experimental result object or the ratation and reduction and enlargement than the standard chain code method.

참고문헌 (Reference)

1 Jing Huang, "Spatial color indexing and applications" 35 (35): 245-268, 1999

2 Dengsheng Zhang, "Shape based image retrieval using generic Fourier descriptor" 17 : 825-842, 2002

3 Vasileios Mezaris, "Region-Based Image Retrieval Using an Object Ontology and Relevance Feedback" 6 : 886-901, 2004

4 Theo Gevers, "PicToSeek: Combining color and shape invariant features for image retrieval" 9 (9): 102-119, 2001

5 Jong-An Park, "Histogram based chain codes for shape description" E86-B (E86-B): 3662-3665, 2003

6 Arnold W.M. Smeulders, "Content-based image retrieval at the end of the early years" 22 (22): 1349-1380, 2000

7 Chabane Djeraba, "Association and content based retrival" 15 (15): 118-135, 2003