DCTNet : A Simple Learning-free Approach for Face Recognition

TL;DR

DCTNet is a learning-free face recognition network using precomputed DCT filters, offering robustness and competitive accuracy compared to PCA-based methods like PCANet.

Contribution

It introduces DCTNet, a data-independent, learning-free face recognition approach using DCT filters, improving robustness and performance over PCA-based methods.

Findings

Achieves comparable or better accuracy than PCANet on benchmark face databases.

Provides robustness when probe images differ significantly from gallery images.

Eliminates the need for training by using precomputed DCT filters.

Abstract

PCANet was proposed as a lightweight deep learning network that mainly leverages Principal Component Analysis (PCA) to learn multistage filter banks followed by binarization and block-wise histograming. PCANet was shown worked surprisingly well in various image classification tasks. However, PCANet is data-dependence hence inflexible. In this paper, we proposed a data-independence network, dubbed DCTNet for face recognition in which we adopt Discrete Cosine Transform (DCT) as filter banks in place of PCA. This is motivated by the fact that 2D DCT basis is indeed a good approximation for high ranked eigenvectors of PCA. Both 2D DCT and PCA resemble a kind of modulated sine-wave patterns, which can be perceived as a bandpass filter bank. DCTNet is free from learning as 2D DCT bases can be computed in advance. Besides that, we also proposed an effective method to regulate the block-wise histogram feature vector of DCTNet for robustness. It is shown to provide surprising performance boost when the probe image is considerably different in appearance from the gallery image. We evaluate the performance of DCTNet extensively on a number of benchmark face databases and being able to achieve on par with or often better accuracy performance than PCANet.