ABSTRACT
This paper proposes to learn parts-based face representation from real face samples and then applies it to face transition. It differs from previous works in two aspects. First, we learn flexible face decomposition from real faces unsupervisedly instead of designing face template manually, for which two simple priors are embedded into learning procedure through constrained EM formulation. Second, both face representation and transition are derived from an unified probabilistic framework. Based on the learned face representation, the face distance measurement could be defined, which enables us to synthesize face via specifying distance with respect to reference faces and depict the full transition trace of two or more given faces with distinct age, gender and race.
- Y. Fu, G. Guo, and T. Huang. Age Synthesis and Estimation via Faces: A Survey. IEEE Trans. on PAMI, 2010. Google ScholarDigital Library
- J. Gra¸ca, K. Ganchev, and B. Taskar. Expectation maximization and posterior constraints. In Proc. of Neural Information Processing System, 2008.Google Scholar
- A. Lanitis, C. Taylor, and T. Cootes. Toward automatic simulation of aging effects on face images. IEEE Trans. on PAMI, pages 442--455, 2002. Google ScholarDigital Library
- D. Ross and R. Zemel. Learning parts-based representations of data. The Journal of Machine Learning Research, 7:2397, 2006. Google ScholarDigital Library
- T. Sim, S. Baker, and M. Bsat. The CMU pose, illumination, and expression (PIE) database. In Proc. of The International Conference on Automatic Face and Gesture Recognition, volume 4, 2002. Google ScholarDigital Library
- Y. Wu, N. Thalmann, and D. Thalmann. A dynamic wrinkle model in facial animation and skin ageing. Journal of Visualization and Computer Animation, 6:195--195, 1995.Google ScholarCross Ref
Index Terms
- Learning parts-based representation for face transition
Recommendations
Unconstrained pose-invariant face recognition by a triplet collaborative dictionary matrix
We propose a novel method for real-world pose-invariant face recognition.Proposed method used from a single image in gallery with any facial expressions.We generate a collaborative dictionary matrix for each people.Promising results were obtained to ...
Pose-robust face recognition via sparse representation
We propose a pose-robust face recognition method to handle the challenging task of face recognition in the presence of large pose difference between gallery and probe faces. The proposed method exploits the sparse property of the representation ...
A paired sparse representation model for robust face recognition from a single sample
Highlights- A paired sparse representation model for still-to-video face recognition, using generic learning and data augmentation to represent both linear and non-...
AbstractSparse representation-based classification (SRC) has been shown to achieve a high level of accuracy in face recognition (FR). However, matching faces captured in unconstrained video against a gallery with a single reference facial ...
Comments