Title :
An effective image shape feature detection and description method
Author :
Xiuxin Chen ; Shiang Wei ; Suxia Xing ; Kebin Jia
Author_Institution :
Coll. of Comput. & Inf. Eng., Beijing Technol. & Bus. Univ., Beijing, China
Abstract :
To solve the problems of complexity and low robustness that exist in present image shape feature detection and description methods, a new image shape feature detection and description method is proposed. First, salient regions are detected using a method based on connected component. Then, a descriptor composed of Hu´s moment invariants and eccentricity is used to descript the detected regions. Experiments show its effectiveness and robustness to translation, rotation and scaling.
Keywords :
computational complexity; feature extraction; shape recognition; Hu moment invariants; complexity; connected component; detected regions; eccentricity; image shape feature description method; image shape feature detection method; low robustness; salient regions; Detectors; Feature extraction; Merging; Robustness; Shape; Testing; Vegetation; Hu´s moment invariants; salient region detection; shape feature exaction;
Conference_Titel :
Mechatronic Science, Electric Engineering and Computer (MEC), 2011 International Conference on
Conference_Location :
Jilin
Print_ISBN :
978-1-61284-719-1
DOI :
10.1109/MEC.2011.6025871
