A Fast Face Detection Method Based on Skin Color
Tao Ji, Wencheng Wang · Journal of Convergence Information Technology · 2011
Abstract To the question of fast face detection, a new method for color facial image is proposed based on skin color segmentation and geometry features. Firstly, a large amount of skin images are analyzed and the skin color model is established for region segmentation. Then, the morphological processing is executed on the binary image which is acquired from binarization operation. After that, the further filtering on facial regions is made by adopting some constraints such as Euler number, the ratio of width and height, the centroid, et al.. Finally, the face region is located and labeled using rectangle. Experimental results showed that the proposed method effectively can equilibrate the unbalance between good accuracy and real-time performance in eye location and is highly efficient in location.