Face Alignment By Discriminative Feature Learning
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)(2019)
摘要
In this paper, we study the effect of discriminative feature learning for face alignment. We claim that features of the same facial landmarks on different images should share similarities at the feature-level. Thus, we propose the Discriminative Feature Learning method (DFL) for face alignment based on the Fully Convolutional Network (FCN). First, the face image is aligned frontal to eliminate the effect of pose and scale. Second, landmark-specific features are extracted from feature maps of the FCN. A distance constraint on landmark features is added to learn discriminative landmark features. Our experiment results show that DFL can effectively improve the performance of face alignment.
更多查看译文
关键词
Face Alignment, Fully Convolutional Network, Discriminative Feature Learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要