DocumentCode :
3207747
Title :
Scale-invariant shape features for recognition of object categories
Author :
Jurie, Frédéric ; Schmid, Cordelia
Author_Institution :
GRAVIR, INRIA-CNRS, Montbonnot, France
Volume :
2
fYear :
2004
fDate :
27 June-2 July 2004
Abstract :
We introduce a new class of distinguished regions based on detecting the most salient convex local arrangements of contours in the image. The regions are used in a similar way to the local interest points extracted from gray-level images, but they capture shape rather than texture. Local convexity is characterized by measuring the extent to which the detected image contours support circle or arc-like local structures at each position and scale in the image. Our saliency measure combines two cost functions defined on the tangential edges near the circle: a tangential-gradient energy term, and an entropy term that ensures local support from a wide range of angular positions around the circle. The detected regions are invariant to scale changes and rotations, and robust against clutter, occlusions and spurious edge detections. Experimental results show very good performance for both shape matching and recognition of object categories.
Keywords :
edge detection; feature extraction; image matching; object detection; convex local arrangements; cost functions; gray-level images; image contours; object category recognition; scale-invariant shape features; shape matching; Character recognition; Computer vision; Cost function; Energy measurement; Entropy; Image edge detection; Object recognition; Position measurement; Robustness; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on
ISSN :
1063-6919
Print_ISBN :
0-7695-2158-4
Type :
conf
DOI :
10.1109/CVPR.2004.1315149
Filename :
1315149
Link To Document :
بازگشت