A Cascaded Noise-Robust Deep CNN for Face Recognition

Xiangbang Meng, Yan Yan, Si Chen, Hanzi Wang

Abstract

State-of-the-art face recognition methods have achieved excellent performance on the clean datasets. However, in real-world applications, the captured face images are usually contaminated with noise, which significantly decreases the performance of these face recognition methods. In this paper, we propose a cascaded noise-robust deep convolutional neural network (CNR-CNN) method, consisting of two sub-networks, i.e., a denoising sub-network and a face recognition sub-network, for face recognition under noise. Instead of separately training the two sub-networks, we jointly train them in a cascaded manner. As a result, the images generated from the denoising sub-network are beneficial to the training of the face recognition sub-network. Furthermore, the dense connectivity is used to concatenate the feature maps layer-by-layer in the denoising sub-network, which can effectively exploit the shallow and deep features of CNN. Experimental results on public face datasets demonstrate the superior performance of the proposed method over several state-of-the-art methods.
BibTeX
@inproceedings{meng2019cascaded,
  author = {Xiangbang Meng and Yan Yan and Si Chen and Hanzi Wang},
  title = {{A Cascaded Noise-Robust Deep CNN for Face Recognition}},
  booktitle = {ICIP},
  year = {2019},
  doi = {10.1109/icip.2019.8803443},
}

Loading related content...

Figure