Sparse Representation-based Classification (SRC) has high recognition performance on face databases. However, the recognition effect of SRC is not ideal for posture changes. In view of the fact that the SRC algorithm cannot solve the problem of offset errors between test samples and training samples, this paper proposes an improved algorithm based on SRC. The algorithm uses each type of training sample as a training dictionary, uses iterative correction and motion offset estimation based on pyramid hierarchical mechanism to obtain the final offset, and finally uses the SRC algorithm to classify the corrected test samples. Experimental results show that this method has good robustness and recognition rate for face images with offset errors.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore