An adaptive bimodal recognition framework using sparse coding for face and ear

@article{Huang2015AnAB,
  title={An adaptive bimodal recognition framework using sparse coding for face and ear},
  author={Zengxi Huang and Yiguang Liu and Xuwei Li and Jie Li},
  journal={Pattern Recognition Letters},
  year={2015},
  volume={53},
  pages={69-76}
}
In this paper, we propose an adaptive face and ear based bimodal recognition framework using sparse coding, namely ABSRC, which can effectively reduce the adverse effect of degraded modality. A unified and reliable biometric quality measure based on sparse coding is presented for both face and ear, which relies on the collaborative representation by all classes. For adaptive feature fusion, a flexible piecewise function is carefully designed to select feature weights based on their qualities… CONTINUE READING