Efficient Face Alignment via Locality-constrained Representation for Robust Recognition

TL;DR

This paper introduces a fast, locality-constrained face alignment algorithm that improves robustness and efficiency in real-time face recognition, especially under severe misalignment conditions.

Contribution

The paper presents the MRLR algorithm, a novel locality-constrained approach that enhances face alignment robustness and computational speed for practical recognition tasks.

Findings

MRLR outperforms state-of-the-art methods in efficiency and scalability.

It achieves better face alignment accuracy under severe misalignments.

Experimental results validate its real-time applicability.

Abstract

Practical face recognition has been studied in the past decades, but still remains an open challenge. Current prevailing approaches have already achieved substantial breakthroughs in recognition accuracy. However, their performance usually drops dramatically if face samples are severely misaligned. To address this problem, we propose a highly efficient misalignment-robust locality-constrained representation (MRLR) algorithm for practical real-time face recognition. Specifically, the locality constraint that activates the most correlated atoms and suppresses the uncorrelated ones, is applied to construct the dictionary for face alignment. Then we simultaneously align the warped face and update the locality-constrained dictionary, eventually obtaining the final alignment. Moreover, we make use of the block structure to accelerate the derived analytical solution. Experimental results on public data sets show that MRLR significantly outperforms several state-of-the-art approaches in terms of efficiency and scalability with even better performance.