Shape description matrix and its applications to color-image retrieval and recognition
- 35 Downloads
Shape description matrix (SDM) describing regional pixel distribution characteristics of images is defined, with both radial and angular distribution messages taken into account to offer a comprehensive and exact description of the shape characteristics even upon a blurred edge. Using this SDM, a general color histogram (GCH) is developed. Both theoretical and experimental results show that the GCH can be applied to color-image retrievals and recognitions with a high efficiency.
KeywordsSDM similarity degree match degree general color histogram
Unable to display preview. Download preview PDF.
- 4.Liang Yanmei, Zhai Hongchen, Mu Guoguang, Image retrieval based on fuzzy relations, Science in China (in Chinese), Ser. E, 2003, 33(8): 934–938.Google Scholar
- 6.Cinque, L., Ciocca, G., Levialdi, S. et al., Color-based image retrieval using spatial-chromatic histograms, Image Vision Computing, 2001, 19:Google Scholar
- 7.Rautiainen, M., Doermann, D., Temporal Color Correlograms for Video Retrieval, Proc. ICPR, 2002, 1(2): 267–272.Google Scholar
- 10.Peng Jinye, Yu Bianzhang, Wang Dakai, Image Similarity detection based on direction gradient angular histogram, Proc. ICPR, 2002, 1(2): 147–153.Google Scholar