A Comprehensive Survey on Pose-Invariant Face Recognition

TL;DR

This paper provides a comprehensive review of pose-invariant face recognition techniques, categorizing existing methods and discussing their advantages, limitations, and future research directions.

Contribution

It offers an extensive survey of established PIFR methods, comparing their strategies and performance to guide future developments in the field.

Findings

Existing methods are grouped into four categories: pose-robust features, multi-view learning, face synthesis, and hybrids.

The paper compares the advantages and limitations of each approach.

Future research directions are identified to address current challenges.

Abstract

The capacity to recognize faces under varied poses is a fundamental human ability that presents a unique challenge for computer vision systems. Compared to frontal face recognition, which has been intensively studied and has gradually matured in the past few decades, pose-invariant face recognition (PIFR) remains a largely unsolved problem. However, PIFR is crucial to realizing the full potential of face recognition for real-world applications, since face recognition is intrinsically a passive biometric technology for recognizing uncooperative subjects. In this paper, we discuss the inherent difficulties in PIFR and present a comprehensive review of established techniques. Existing PIFR methods can be grouped into four categories, i.e., pose-robust feature extraction approaches, multi-view subspace learning approaches, face synthesis approaches, and hybrid approaches. The motivations, strategies, pros/cons, and performance of representative approaches are described and compared. Moreover, promising directions for future research are discussed.