PROJECT TITLE :
Undersampled Face Recognition via Robust Auxiliary Dictionary Learning
During this paper, we tend to address the problem of sturdy face recognition with undersampled coaching data. Given solely one or few training images on the market per subject, we have a tendency to gift a unique recognition approach, which not solely handles check pictures with large intraclass variations such as illumination and expression. The proposed technique is also to handle the corrupted ones due to occlusion or disguise, which is not present during training. This is achieved by the learning of a sturdy auxiliary dictionary from the subjects not of interest. Along with the undersampled training knowledge, each intra and interclass variations will therefore be successfully handled, while the unseen occlusions will be automatically disregarded for improved recognition. Our experiments on four face image datasets ensure the effectiveness and robustness of our approach, that is shown to outperform state-of-the-art sparse representation-primarily based ways.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here