ComplexFace: a Multi-Representation Approach for Image Classification with Small Dataset

TL;DR

ComplexFace introduces a novel complex number-based data augmentation method for face recognition with small datasets, significantly improving accuracy over existing approaches.

Contribution

The paper proposes a new complex number-based data augmentation and fusion technique for face recognition with limited samples, enhancing classification performance.

Findings

Achieved up to 84.80% error reduction on ORL database.

Significantly outperformed existing methods on GT and ORL datasets.

Reduced average errors from over 30% to around 14% on GT database.

Abstract

State-of-the-art face recognition algorithms are able to achieve good performance when sufficient training images are provided. Unfortunately, the number of facial images is limited in some real face recognition applications. In this paper, we propose ComplexFace, a novel and effective algorithm for face recognition with limited samples using complex number based data augmentation. The algorithm first generates new representations from original samples and then fuse both into complex numbers, which avoids the difficulty of weight setting in other fusion approaches. A test sample can then be expressed by the linear combination of all the training samples, which mapped the sample to the new representation space for classification by the kernel function. The collaborative representation based classifier is then built to make predictions. Extensive experiments on the Georgia Tech (GT) face database and the ORL face database show that our algorithm significantly outperforms existing methods: the average errors of previous approaches ranging from 31.66% to 41.75% are reduced to 14.54% over the GT database; the average errors of previous approaches ranging from 5.21% to 10.99% are reduced to 1.67% over the ORL database. In other words, our algorithm has decreased the average errors by up to 84.80% on the ORL database.