Title :
Shape Descriptor Based on Structural Curvature Histogram for Image Retrieval
Author :
Xie, Yonghua ; OhEigeartaigh, Micheal
fDate :
March 31 2009-April 2 2009
Abstract :
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.
Keywords :
content-based retrieval; edge detection; image retrieval; gray image retrieval; image contour curvature vector; image rotation; scaling transform; shape descriptor; spatial structural information; structural curvature histogram; Application software; Computer science; Content based retrieval; Data mining; Histograms; Image retrieval; Information retrieval; Robustness; Shape; Space technology;
Conference_Titel :
Computer Science and Information Engineering, 2009 WRI World Congress on
Conference_Location :
Los Angeles, CA
Print_ISBN :
978-0-7695-3507-4
DOI :
10.1109/CSIE.2009.242