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

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

11 Scopus Citations
View graph of relations

Related Research Unit(s)


Original languageEnglish
Article number107176
Journal / PublicationPattern Recognition
Online published16 Dec 2019
Publication statusPublished - Apr 2020


Training deep convolutional neural networks (CNNs) often requires high computational cost and a large number of learnable parameters. To overcome this limitation, one solution is computing predefined convolution kernels from training data. In this paper, we propose a novel three-stage approach for filter learning alternatively. It learns filters in multiple structures including standard filters, channel-wise filters and point-wise filters which are inspired from variations of CNNs’ convolution operations. By analyzing the linear combination between learned filters and original convolution kernels in pre-trained CNNs, the reconstruction error is minimized to determine the most representative filters from the filter bank. These filters are used to build a network followed by HOG-based feature extraction for feature representation. The proposed approach shows competitive performance on color face recognition compared with other deep CNNs-based methods. Besides, it provides a perspective of interpreting CNNs by introducing the concepts of advanced convolutional layers to unsupervised filter learning.

Research Area(s)

  • Deepeigen-filters, Convolution kernels, Face recognition, Convolutional neural networks, Feature representation