A Comprehensive Survey on Pose-Invariant Face Recognition

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.

Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification

“…Former studies have shown that, when a large number of representative training images are available, computer algorithms are able to recognize even better than humans [6], [7], [25], [27], [33]. These algorithms, before recognizing, represent the face in the feature space, and perhaps because they are able to extract information from training images about the changes caused by different conditions they outperform humans in recognition [25].…”

Opportunity and challenge on face recognition: generic-to-specific feature representation and recognition strategy

“…For more than four decades, research on face recognition techniques by computers has become one of the studies in the field of computer vision studied by many researchers [1]. Face recognition closely related to Biometrics, an identity recognition mechanism using physical characteristics.…”

“…Various alternative recognition systems that are highly reliable such as fingerprint, retina and palm-hand already implemented for various needs, but recognition based-on face has several advantages. In face recognition, data acquisition mechanisms can be performed without the cooperation of the subject to be identified [1][2] [3], in contrast to the recognition system using fingerprints, retinas and palms, where the data acquisition process is highly dependent on the cooperation of the person / subject to be identified. Although data acquisition performed without the cooperation of the subject for identified, the quality of the acquisition data is at an acceptable level for the recognition process.…”

“…Although data acquisition performed without the cooperation of the subject for identified, the quality of the acquisition data is at an acceptable level for the recognition process. The characteristics of the data acquisition process are not intrusive, which is particularly suitable for the development of seamless search / recognition systems such as surveillance security, border control, forensics, digital entertainment and more [1][2] [3]. Another advantage of face-based recognition is the proximity to human identification, where face-based recognition is the most natural form of recognition [4], this is in line with the ultimate goal in the field of computer vision, which synthesizes / mimics the way human recognize object-using sense of sight.…”

A Novel Approach to Mugshot Based Arbitrary View Face Recognition

“…The frontal and profile face images provide complementary information of the face, and are thus believed to be useful for pose-robust face recognition if both of them are effectively utilized. However, most existing automated face recognition methods [1][2][3] are devised for the scenario of only frontal face images in the gallery. To recognize non-frontal faces, they usually adopt one of the following three ways: (i) Normalizing the non-frontal probe face to frontal pose and matching it to the enrolled frontal faces [4][5][6], (ii) Generating synthetic face images from the frontal faces in the gallery according to the pose of the probe face, and then comparing the probe face with these synthetic face images [7,8], (iii) Extracting pose-adaptive features directly from the gallery and probe face images for comparison [9,10].…”