Title :
A Method of Eye Location Based on Image Complexity
Author_Institution :
Hang Zhou Inst. of Commerce, Zhejiang Gongshang Univ., Hangzhou, China
Abstract :
Eye location in face recognition is widely used in machine vision. On the basis of the characteristic that the changes of the human eye grey scale are very obvious, the present article brings forward a new algorithm of eye location in face recognition. Firstly, we divide the searched area of eyes into small patches, and calculate the degree of image complexity of each small patch; then find the 16 patches with largest image complexity; lastly, locate eyes accurately according to the structural centralization degree of image patches. Compared with other methods, this algorithm has characteristics of accurate location and high arithmetic speed.
Keywords :
eye; face recognition; image colour analysis; eye location; face recognition; human eye grey scale; image complexity; image patch; machine vision; structural centralization degree; Arithmetic; Business; Data mining; Eyes; Face recognition; Humans; Image segmentation; Machine vision; Statistical learning; Videophone systems; eye location; face recognition; image complexity;
Conference_Titel :
Environmental Science and Information Application Technology, 2009. ESIAT 2009. International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-3682-8
DOI :
10.1109/ESIAT.2009.254
