Computer Science and Information Engineering, World Congress on (2009)
Los Angeles, California USA
Mar. 31, 2009 to Apr. 2, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CSIE.2009.242
This paper presents a new shape descriptor based on structural curvature histogram (SCHD) for gray image retrieval. With this method, the image contour curvature vector containing spatial structural information is firstly extracted, and then the shape descriptor based on the equalized structural curvature histogram is obtained for image retrieval application. Experimental results show that the presented structural curvature histogram descriptor is robust to image rotation, scaling transform and contour starting point, and can bring about good retrieval precision and speed simultaneously.
Y. Xie and M. OhEigeartaigh, "Shape Descriptor Based on Structural Curvature Histogram for Image Retrieval," 2009 WRI World Congress on Computer Science and Information Engineering, CSIE(CSIE), Los Angeles, CA, 2009, pp. 411-415.