生物特征识别技术作为一种身份鉴别手段具有独特的优势。在生物特征识别系统中,采集数据的预处理是不可或缺的环节。以人脸识别为例,介绍了一种在复杂背景的彩色图像中,基于颜色和知识的生物特征预处理方法。首先利用颜色信息从图像中分割出类肤色区域,然后运用人脸几何特征和眼睛的提取定位人脸。仿真实验表明,该算法能较为准确地定位彩色图像中的正面或小角度偏转的人脸,具有较快的运算速度。
Biometrics which is used as a method of personal identity authentication have unique advantages. In the biometric identification systems, the pretreatment for the collected data is necessary. In the example of face recognition, the pretreatment of biometrics for the color image with complex background which is based on color and knowledge is introduced. Firstly, the color information is used to acquire possible skin regions in the original image. Then, the face regions are located by facial geometrical information and the eyes extraction. Experimental results show that the proposed approach can locate positive or rotated face with little angle in a given image, and at the same time, a faster speed of the face location is achieved.