1. Face Alignment Using Boosting and Evolutionary Search
- Author
-
Zhang, Hua, Liu, Duanduan, Poel, Mannes, Nijholt, Antinus, Zha, H., Taniguchi, R.-I., and Maybank, S.
- Subjects
Boosting (machine learning) ,granular features ,business.industry ,Feature vector ,evolutionary search ,boosting appearance models ,Brute-force search ,Pattern recognition ,HMI-MI: MULTIMODAL INTERACTIONS ,Machine learning ,computer.software_genre ,EC Grant Agreement nr.: FP6/033812 ,Active appearance model ,EWI-16061 ,Discriminative model ,Face model ,Search algorithm ,IR-71163 ,Artificial intelligence ,business ,computer ,Classifier (UML) ,Face alignment ,Mathematics ,METIS-270691 - Abstract
In this paper, we present a face alignment approach using granular features, boosting, and an evolutionary search algorithm. Active Appearance Models (AAM) integrate a shape-texture-combined morphable face model into an efficient fitting strategy, then Boosting Appearance Models (BAM) consider the face alignment problem as a process of maximizing the response from a boosting classifier. Enlightened by AAM and BAM, we present a framework which implements improved boosting classifiers based on more discriminative features and exhaustive search strategies. In this paper, we utilize granular features to replace the conventional rectangular Haar-like features, to improve discriminability, computational efficiency, and a larger search space. At the same time, we adopt the evolutionary search process to solve the deficiency of searching in the large feature space. Finally, we test our approach on a series of challenging data sets, to show the accuracy and efficiency on versatile face images.
- Published
- 2010