Face Alignment by Discriminative Feature Learning
Autor: | Haoji Hu, Qiang Zhou, Weiliang Chen |
---|---|
Rok vydání: | 2019 |
Předmět: |
021110 strategic
defence & security studies business.industry Computer science Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 0211 other engineering and technologies Pattern recognition 02 engineering and technology Discriminative model 0202 electrical engineering electronic engineering information engineering Entropy (information theory) 020201 artificial intelligence & image processing Artificial intelligence business Feature learning |
Zdroj: | ICIP |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |