Cascaded Asymmetric Local Pattern: A Novel Descriptor for Unconstrained Facial Image Recognition and Retrieval

TL;DR

This paper introduces a new hand-crafted facial image descriptor called Cascaded Asymmetric Local Pattern (CALP) that improves recognition accuracy under challenging environmental and physiological variations.

Contribution

The paper presents a novel cascaded asymmetric local pattern descriptor that encodes pixel relationships in horizontal and vertical directions, outperforming existing descriptors in unconstrained facial recognition.

Findings

CALP outperforms state-of-the-art descriptors on challenging datasets.

It shows significant robustness against variations in illumination, pose, and expression.

The descriptor has an optimal feature length for effective recognition.

Abstract

Feature description is one of the most frequently studied areas in the expert systems and machine learning. Effective encoding of the images is an essential requirement for accurate matching. These encoding schemes play a significant role in recognition and retrieval systems. Facial recognition systems should be effective enough to accurately recognize individuals under intrinsic and extrinsic variations of the system. The templates or descriptors used in these systems encode spatial relationships of the pixels in the local neighbourhood of an image. Features encoded using these hand crafted descriptors should be robust against variations such as; illumination, background, poses, and expressions. In this paper a novel hand crafted cascaded asymmetric local pattern (CALP) is proposed for retrieval and recognition facial image. The proposed descriptor uniquely encodes relationship amongst the neighbouring pixels in horizontal and vertical directions. The proposed encoding scheme has optimum feature length and shows significant improvement in accuracy under environmental and physiological changes in a facial image. State of the art hand crafted descriptors namely; LBP, LDGP, CSLBP, SLBP and CSLTP are compared with the proposed descriptor on most challenging datasets namely; Caltech-face, LFW, and CASIA-face-v5. Result analysis shows that, the proposed descriptor outperforms state of the art under uncontrolled variations in expressions, background, pose and illumination.