Discriminative Residual Analysis for Image Set Classification with Posture and Age Variations

TL;DR

This paper introduces a Discriminant Residual Analysis method to enhance image set classification by extracting discriminant features, effectively handling variations like posture and age, and demonstrating superior performance on benchmark datasets.

Contribution

The paper proposes a novel Discriminant Residual Analysis technique that projects residual representations into a discriminant subspace, improving classification accuracy under complex variations.

Findings

Outperforms existing methods on benchmark datasets

Effectively handles posture and age variations

Reduces sampling errors with a nonfeasance strategy

Abstract

Image set recognition has been widely applied in many practical problems like real-time video retrieval and image caption tasks. Due to its superior performance, it has grown into a significant topic in recent years. However, images with complicated variations, e.g., postures and human ages, are difficult to address, as these variations are continuous and gradual with respect to image appearance. Consequently, the crucial point of image set recognition is to mine the intrinsic connection or structural information from the image batches with variations. In this work, a Discriminant Residual Analysis (DRA) method is proposed to improve the classification performance by discovering discriminant features in related and unrelated groups. Specifically, DRA attempts to obtain a powerful projection which casts the residual representations into a discriminant subspace. Such a projection subspace is expected to magnify the useful information of the input space as much as possible, then the relation between the training set and the test set described by the given metric or distance will be more precise in the discriminant subspace. We also propose a nonfeasance strategy by defining another approach to construct the unrelated groups, which help to reduce furthermore the cost of sampling errors. Two regularization approaches are used to deal with the probable small sample size problem. Extensive experiments are conducted on benchmark databases, and the results show superiority and efficiency of the new methods.