中文摘要：

针对传统方法合成的正面人脸图像中信息丢失和变形的问题, 提出了-种基于筛选评估准则的非正面人脸图像合成方法. 人脸筛选评估准则融合了脸部对称性、正脸差异水平和人脸水平扭转角度3 方面信息,其中人脸水平扭转角度利用细节上的眼部信息来评价人脸的正面水平, 而脸部对称性和正脸差异水平分别对人脸的左右和垂直方向进行整体评价, 综合这三方面信息可有效地排除低质量侧脸图像对合成正脸图像的干扰. 首先进行标记点检测跟踪,然后基于此对同一人的多幅侧脸图像进行筛选,最后进行插值运算合成正面人脸,并在FERET 图像库中对该方法进行实验验证. 结果表明：通过本文筛选准则可有效滤除合成中低质量、强干扰的侧脸图像,可降低姿态问题对人脸识别精度的干扰,最终合成精确逼近真实正面人脸的合成图像.

英文摘要：

To solve the problem of information missing and deformation of the traditional synthesized frontal face image, anon-frontal face image synthesis method based on source screening criteria is proposed. The source screeningcriteria combines the facial symmetry, the frontal face image differences level and the horizontal rotating angle.The horizontal rotating angle uses the details of the eye information to assess the level of the front face. The leftto-right and vertical direction is separately assessed according to the facial symmetry and the frontal face imagedifferences level. Combining these three aspects can availably exclude interference of low-quality non-frontalface image in synthesizing the frontal face. Firstly, marking points are detected and tracked. Then, multi-viewface images of same person are screened to obtain the high-quality, low-interference non-frontal face images asthe best synthetic input source images. Finally, frontal face images are synthesized by calculated interpolation.Experimental findings on the FERET databases demonstrate that the source screening criteria can availablyscreen out low-quality, strong-interference non-frontal face images and reduce the impact of pose questions onthe precision of face recognition algorithm effectively. The synthesized frontal view face can approximate theground truth frontal view face.