Multi-Pose Face Recognition Using Hybrid Face Features Descriptor

TL;DR

This paper introduces a hybrid face features descriptor (HFFD) for multi-pose face recognition, combining wavelet and DCT features to improve recognition accuracy across different face poses.

Contribution

The paper proposes a novel hybrid face features descriptor that fuses frequency-based features from wavelet and DCT analyses to enhance multi-pose face recognition performance.

Findings

HFFD achieves better accuracy than recent 2D face recognition methods.

HFFD effectively handles large face pose variations.

The method maintains reasonable performance across multiple poses.

Abstract

This paper presents a multi-pose face recognition approach using hybrid face features descriptors (HFFD). The HFFD is a face descriptor containing of rich discriminant information that is created by fusing some frequency-based features extracted using both wavelet and DCT analysis of several different poses of 2D face images. The main aim of this method is to represent the multi-pose face images using a dominant frequency component with still having reasonable achievement compared to the recent multi-pose face recognition methods. The HFFD based face recognition tends to achieve better performance than that of the recent 2D-based face recognition method. In addition, the HFFD-based face recognition also is sufficiently to handle large face variability due to face pose variations .