Deep eigen-filters for face recognition: Feature representation via unsupervised multi-structure filter learning

作者：

Highlights：

• Propose a three-stage multi-structure filter learning approach inspired from advances in convolutional layers of convolutional neural networks.

• Analyze the linear combination between obtained filters and convolution kernels in convolutional neural networks for filter selection.

• Build a network for feature representation based on learned filters.

• Competitive face recognition performance with less computational cost and high robustness to facial expression and illumination compared to other deep learning-based methods.

摘要

•Propose a three-stage multi-structure filter learning approach inspired from advances in convolutional layers of convolutional neural networks.•Analyze the linear combination between obtained filters and convolution kernels in convolutional neural networks for filter selection.•Build a network for feature representation based on learned filters.•Competitive face recognition performance with less computational cost and high robustness to facial expression and illumination compared to other deep learning-based methods.

论文关键词：Deep eigen-filters,Convolution kernels,Face recognition,Convolutional neural networks,Feature representation

论文评审过程：Received 3 September 2019, Revised 28 November 2019, Accepted 15 December 2019, Available online 16 December 2019, Version of Record 23 December 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107176