To search, Click below search items.


All Published Papers Search Service


Eyes Location by Neural Network-based Face Segmentation


Xiao-yi Feng


Vol. 6  No. 5  pp. 132-135


This paper proposed a neural network-based face segmentation method for eyes location. After face is detected, it is segmented automatically by a competitive Hopfield neural network (CHNN) and the facial feature candidates such as eyes, eyebrows and mouth are obtained, and then eyes are located by facial features evaluation and validation, which is based on face’s geometrical structures. To enhance the difference between facial features and other face area, the color face image is converted into a color-ratio grey image before face segmentation. Experimental results show that the proposed system performs well.


Competitive Hopfield neural network, Eyes location, Face segmentation, color-ratio image