Discriminative Structured Dictionary Learning for Face Recognition
For a few years, plenty of face recognition algorithms, such as deep learning, have been in hot pursuit with the trend of the technology, while dictionary learning algorithm is still out of the woods for the sake of its higher robustness to occlusion and light. In this paper, we propose to learn a discriminative structured dictionary with constraint named as multi-label to suppress representations for different classes, as well as Laplacian Eigenmaps to encourage the representations for the same class to be close to each other. Demonstrated by the results of the experiments, our proposed dictionary learning methods intend to achieve better classification performance and higher computational efficiency compared to the existing algorithms.
KeywordsDictionary learning Supervised learning Face recognition Laplacian Eigenmaps
- 6.Li, H., Liu, F.: Image denoising via sparse and redundant representations over learned dictionaries in wavelet domain. In: Proceedings of the 5th International Conference on Image Graphics ICIG 2009, vol. 15, no. 12, pp. 754–758 (2010)Google Scholar
- 8.Ramirez, I., Sprechmann, P., Sapiro, G.: Classification and clustering via dictionary learning with structured incoherence and shared features. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3501–3508 (2010)Google Scholar
- 10.Zhang, Q., Li, B.: Discriminative K-SVD for dictionary learning in face recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2691–2698 (2010)Google Scholar
- 12.Yang, M., Zhang, L., Feng, X., Zhang, D.: Fisher discrimination dictionary learning for sparse representation. In: 2011 International Conference on Computer Vision, pp. 543–550 (2011)Google Scholar