Title :
Target recognition of household service robot based on shape moment invariants
Author :
Hao, Wang ; Xiao-Rong, Hu ; Bao-Fu, Fang ; Wei, Geng ; Fan-Hui, Meng
Author_Institution :
Sch. of Comput. & Inf., Hefei Univ. of Technol., Hefei, China
Abstract :
Target recognition technology is a difficulty in the research field of household service robot. In this paper, connected domains are picked out on the basis of color image segmentation, denoising and graying. The algorithm has improved through shape moment invariants and weighting Euclidean distance. The experiment results show that this algorithm is not sensitive to the light conditions and the perspective of camera. Furthermore, this algorithm has big advantage to distinguish objects with similar color and it is efficient, accurate and robust.
Keywords :
image colour analysis; image denoising; image recognition; image segmentation; robot vision; service robots; color image segmentation; household service robot; image denoising; image graying; shape moment invariants; target recognition technology; weighting Euclidean distance; Noise reduction; Shape; image processing; shape moment invariants; target recognition; weighting Euclidean distance;
Conference_Titel :
Computer Application and System Modeling (ICCASM), 2010 International Conference on
Conference_Location :
Taiyuan
Print_ISBN :
978-1-4244-7235-2
Electronic_ISBN :
978-1-4244-7237-6
DOI :
10.1109/ICCASM.2010.5622885
