Gabor feature based sparse representation for face recognition with Gabor occlusion dictionary

Description

In this project, we proposed a Gabor-feature based SRC (GSRC) scheme, which uses the image local Gabor features for SRC, and proposed an associated Gabor occlusion dictionary computing algorithm to handle the occluded face images.
Apart from the improved face recognition rate, one important advantage of GSRC is its compact occlusion dictionary, which has much less atoms than that of the original SRC scheme. This greatly reduces the computational cost of sparse coding. We evaluated the proposed method on different conditions, including
variations of illumination, expression and pose, as well as block occlusion and disguise. The experimental results clearly demonstrated that the proposed GSRC has much better performance than SRC, leading to much higher recognition rates while spending much less computational cost. This makes it much more practicable to use than SRC in real world face recognition.

ref :

Yang, Meng, and Lei Zhang. “Gabor feature based sparse representation for face recognition with gabor occlusion dictionary.” In European conference on computer vision, pp. 448-461. Springer, Berlin, Heidelberg, 2010.

Nonlocally centralized sparse representation for image interpolation

Metasample Based Sparse Representation for Tumor Classification