A Method of Eyes and Mouth Corner Location in Identity Photographs
ZHU Xiao-yuan,ZHAO Jing-xiu(School of Computer Science,Qufu Normal University,Rizhao 276826,China)
This paper presents a simple and effective method for locating eyes and mouth corners based on standard students' color documents.Firstly,executing brightness adjustment and color space conversion for images.Then,segmenting the image according to the skin-color's clustering characteristic in the YCbCr color space,and dealing with the detected region through the mathematical morphology operations.Finally,accurately positioning the location of eyes and mouth corners in a small range using the structural characteristics and geometric distribution rules of the face.Experimental results show that this method achieves better location rate for images with noise and a certain expression,and it is simple compared to traditional methods.
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.