研究描述人脸特征的有效方法, 讨论身份证照片的特征提取和检索采用自适应肤色检测技术改进通用的肤色检测算法, 进行脸部区域的划分提出系数投影法对面部五官区域进行分割, 在各区域中提取面部几何特征引人描述脸颊和下额轮廓的曲线参数作为脸形特征, 得到对人脸特征更准确的描述将面部几何特征矢量匹配、脸形曲线参数匹配和脸部图像相关匹配相结合, 实现人像照片的准确检索实验表明该方法性能优良。-Describe the facial features of an effective way to discuss the ID card photo feature extraction and retrieval using adaptive skin color detection techniques improve the general detection algorithm for facial areas by the proposed coefficient of projection of the facial features to segment the region, in the Extraction of geometric features of the region face cheeks and under the places described in the introduction of profile parameters of the curve as facial features, facial features and get the more accurate descr iption of the feature vector matching facial geometry, face curve parameter matching and matching facial images related to the combination of to achieve an accurate portrait photo retrieval experiments show that the method excellent.