Collaborative Representation Classification Ensemble for Face Recognition

TL;DR

This paper introduces an ensemble of Collaborative Representation Classification models using diverse biologically-inspired features to significantly improve face recognition accuracy and robustness.

Contribution

It proposes a novel weighted ensemble approach for CRC models with different features, enhancing recognition performance beyond individual models.

Findings

Ensemble method outperforms single CRC models.

Weighted ensemble improves recognition accuracy.

Method is effective across various experiments.

Abstract

Collaborative Representation Classification (CRC) for face recognition attracts a lot attention recently due to its good recognition performance and fast speed. Compared to Sparse Representation Classification (SRC), CRC achieves a comparable recognition performance with 10-1000 times faster speed. In this paper, we propose to ensemble several CRC models to promote the recognition rate, where each CRC model uses different and divergent randomly generated biologically-inspired features as the face representation. The proposed ensemble algorithm calculates an ensemble weight for each CRC model that guided by the underlying classification rule of CRC. The obtained weights reflect the confidences of those CRC models where the more confident CRC models have larger weights. The proposed weighted ensemble method proves to be very effective and improves the performance of each CRC model significantly. Extensive experiments are conducted to show the superior performance of the proposed method.