The Human Face Recognition Algorithm Based on the Improved Binary Morphology

Aimed at the problems existing in the human face recognition algorithm, namely the low recognition rate and the image being easily influenced by the factors such as lighting and brightness, this paper has proposed a human face recognition algorithm combining the skin color detection algorithm and binary morphology processing algorithm. First of all, the captured images will go through the YCrCb model detection to reduce the effect of brightness on the image. HSV model detection algorithm has been adopted to reduce the effect of lighting on the image. The detection image gained will be transformed into the binary image. The denoising of binary morphology will be also conducted, thus gaining the human face recognition image. The experimental results show that the algorithm proposed in this paper can achieve the detection and recognition rate of 98.6 percent, 93.3 percent and 90 percent respectively for uncomplicated human face image, relatively complicated human face image and complicated human face image.