A novel network model based ICA filter for face recognition

Despite the great success of deep learning convolution networks, researchers are not yet clear about its feature learning mechanism and optimal network configuration. In this paper, we present a cascaded linear convolution network based on ICA filters, termed ICANet. ICANet mainly includes three parts: convolution layer, binary hash and block histogram. The results show that ICANet has a very good performance in face recognition tasks.

[1]  Xiaoyang Tan,et al.  Fusing Gabor and LBP Feature Sets for Kernel-Based Face Recognition , 2007, AMFG.

[2]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Jonghyun Choi,et al.  Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Neural Networks , 2013 .

[6]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[7]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[8]  Jie Chen,et al.  Fusing Local Patterns of Gabor Magnitude and Phase for Face Recognition , 2010, IEEE Transactions on Image Processing.

[9]  Xiaogang Wang,et al.  Deep Learning Face Representation from Predicting 10,000 Classes , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Jiwen Lu,et al.  PCANet: A Simple Deep Learning Baseline for Image Classification? , 2014, IEEE Transactions on Image Processing.