摘要
随着多视角人脸识别技术需求的不断增长,正面人脸图像合成成了热门的研究课题。然而,从侧面人脸图像准确地合成出正面人脸是一个典型的逆向问题,具有较大的挑战性。对目前正脸图像合成方法进行了系统总结,介绍了几种典型的合成策略,并对这些方法按原理分成了基于图形学的方法和基于统计学习的方法两类分别进行研究。此外,还从算法复杂性、鲁棒性,以及图像合成效果等方面对现有正面人脸图像合成算法进行了对比研究,给出了未来可能的研究方向。
With the increasing demand for multi-view face recognition techniques, frontal face image synthesis has been one of the most interesting research topics nowadays. However, it is a classic inverse problem to synthesize frontal images from profiles accurately, and there are some challenges. In this paper, we present a systematical summary of the current frontal image synthesis methods. Furthermore, some classic synthesis strategies are introduced. Moreover, according to the theories used, the methods are classified into two categories： graphic based methods and statistical learning based methods. Additionally, these approaches are compared in three aspects： complicacy, robustness, and performance. At last, some potential pointers towards future research topics are given.
出处
《中国图象图形学报》
CSCD
北大核心
2013年第1期1-10,共10页
Journal of Image and Graphics
基金
国家杰出青年科学基金项目(61125204)
国家自然科学基金项目(61172146)
陕西省自然科学基础研究计划(2009JM8004)
关键词
人脸合成
多视角
逆问题
综述
face synthesis
multi-view
inverse problem
review
