Handcraft and Learned Feature Extraction Techniques for Robust Face Recognition : A Review

Abstract

In this paper, we will review face representation techniques that are used in face recognition process. There are two types of feature extraction: handcraft and learned features. PCA and LBP are handcraft feature extraction while the DeepFace, generating from convolutional neural network, is learned feature. PCA is an orthogonal transformation where a set of observations is converted to the principal components. The first few principal components have the largest variance hence represented images with small number of features. LBP is a local binary pattern which encodes local image into a binary pattern. LBP tolerates against changes in gray scale variations. By allowing the deep learning to automatically discover the image representations from raw data therefore DeepFace is a learned feature. In some cases, data may be unable to define specific feature especially for face representation. DeepFace is an alternative technique where features are generated through training/learning process without relying on specific algorithms. Learned features significantly outperform the handcraft one where the test set is unseen. PCA, LBP and DeepFace will be compared in terms of accuracy and computational time.