ICANet: a simple cascade linear convolution network for face recognition

Yongqing Zhang,Xi Wu,Jiliu Zhou,Dongrui Gao,Tianyu Geng

doi:10.1186/s13640-018-0288-4

Abstract

Recently, deep convolutional networks have demonstrated their capability of improving the discriminative power compared with other machine learning method, but its feature learning mechanism is not very clear. In this paper, we present a cascaded linear convolutional network, based on independent component analysis (ICA) filters, named ICANet. ICANet consists of three parts: a convolutional layer, a binary hash, and a block histogram. It has the following advantages over other methods: (1) the network structure is simple and computationally efficient, (2) the ICA filter is trained with an unsupervised algorithm using unlabeled samples, which is practical, and (3) compared to deep learning models, each layer parameter in ICANet can be easily trained. Thus, ICANet can be used as a benchmark for the application of a deep learning framework for large-scale image classification. Finally, we test two public databases, AR and FERET, showing that ICANet performs well in facial recognition tasks.

Highlights

Convolutional neural networks is a well-known deep learning architecture that has been extensively applied to image recognition
Histogram block size had an impact on Independent Component Analysis Network (ICANet), where block histograms overlapped slightly to improve recognition performance
The number of filters is an important factor for the recognition performance in the convolutional layer on ICANet, because there are more binary images encoded and the amount of information increased when the number of filters in the first stage gradually increased

Summary

Introduction

Convolutional neural networks is a well-known deep learning architecture that has been extensively applied to image recognition. A wide range of attention has been paid to the academe and industry [1–3]. The most important reason is that the deep convolution networks can automatically extract and learn hidden representations of data on a number of blocks consisting of convolutional layer, activation function layer, and max pooling layer. How to choose properly parameters and configurations, including the filter sizes, the number of layers, and the pooling function, is a big challenge. AlexNet [1] outpaced LeNet [4] in the ImageNet Large Scale Visual Recognition Challenge in 2012. The network structure of AlexNet is growing deeper

Methods

Results

Conclusion