Title :
A extraction method of human head in complex background
Author :
Peng, Yan ; Chen, Feng ; Ouyang, Minzi
Author_Institution :
Comput. Sci. Coll., Sichuan Univ. of Sci. & Eng., Zigong, China
Abstract :
For face detection in complex background environment, this paper proposed one method of human head´s accurate localization based on background difference method and the improved convex combination template. Effective image can be obtained through the image preprocessing. We can gain the human body contours by using the background difference method, then initially ascertained the position of human head by utilizing the relative relationship between human head and torso, also made use of fuzzy clustering convex combination template to get the exact position of the head. Experimental results show that the method can improve the body and head positioning algorithm speed and accuracy.
Keywords :
face recognition; feature extraction; fuzzy set theory; image resolution; pattern clustering; complex background; convex combination; extraction method; face detection; fuzzy clustering; human head localization; human torso; image preprocessing; Head; Morphology; Torso; Extraction of human head image; background difference method; convex type combination template; fuzzy clustering;
Conference_Titel :
Intelligent Computing and Intelligent Systems (ICIS), 2010 IEEE International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4244-6582-8
DOI :
10.1109/ICICISYS.2010.5658832