Title :
Human Face Location Based on Gradient Distributions
Author :
Bao-jian, Zhang ; Guohong, Gao ; Jinna, Lv ; Yanli, Zhu
Author_Institution :
Coll. of Inf. & Eng., Henan Inst. of Sci. & Technol., Xinxiang, China
Abstract :
In this paper a fast face location method based on gradient distributions is presented. This method can locate face with certain rotation, or light variation or with glasses or beard in the image. It begins with vertical location by use of vertical integral projection on the two-valued image of the original image, and then proceeds with horizontal location according to the distributions of gradient direction. Experiments have proved this method fast and efficient.
Keywords :
face recognition; gradient methods; fast face location; gradient direction; gradient distribution; horizontal location; human face location; two-valued image; vertical integral projection; Data engineering; Data mining; Data preprocessing; Educational institutions; Face recognition; Glass; Gray-scale; Humans; Knowledge engineering; Optimization methods; Face location; gradient direction; margin extracting; threshold;
Conference_Titel :
Knowledge Discovery and Data Mining, 2010. WKDD '10. Third International Conference on
Conference_Location :
Phuket
Print_ISBN :
978-1-4244-5397-9
Electronic_ISBN :
978-1-4244-5398-6
DOI :
10.1109/WKDD.2010.130