Face Image Classification by Pooling Raw Features

TL;DR

This paper introduces a simple, efficient face recognition feature extraction method based on spatial pyramid pooling of local patches, achieving state-of-the-art results with minimal complexity.

Contribution

The paper presents a novel, straightforward feature pooling approach for face recognition that outperforms recent methods without requiring learning, relying mainly on spatial pyramid pooling and PCA whitening.

Findings

Significant accuracy improvements on FERET and LFW-a datasets.

Simple implementation with about 20 lines of code.

Critical role of multi-level pooling and patch normalization.

Abstract

We propose a very simple, efficient yet surprisingly effective feature extraction method for face recognition (about 20 lines of Matlab code), which is mainly inspired by spatial pyramid pooling in generic image classification. We show that features formed by simply pooling local patches over a multi-level pyramid, coupled with a linear classifier, can significantly outperform most recent face recognition methods. The simplicity of our feature extraction procedure is demonstrated by the fact that no learning is involved (except PCA whitening). We show that, multi-level spatial pooling and dense extraction of multi-scale patches play critical roles in face image classification. The extracted facial features can capture strong structural information of individual faces with no label information being used. We also find that, pre-processing on local image patches such as contrast normalization can have an important impact on the classification accuracy. In particular, on the challenging face recognition datasets of FERET and LFW-a, our method improves previous best results by more than 10% and 20%, respectively.