Abstract
The aim of this work is to carry out a comparative study of face recognition methods that are suitable to work in unconstrained environments. The analyzed methods are selected by considering their performance in former comparative studies, in addition to be real-time, to require just one image per person, and to be fully online. In the study two local-matching methods, histograms of LBP features and Gabor Jet descriptors, one holistic method, generalized PCA, and two image-matching methods, SIFT-based and ERCF-based, are analyzed. The methods are compared using the FERET, LFW, UCHFaceHRI, and FRGC databases, which allows evaluating them in real-world conditions that include variations in scale, pose, lighting, focus, resolution, facial expression, accessories, makeup, occlusions, background and photographic quality. Main conclusions of this study are: there is a large dependence of the methods on the amount of face and background information that is included in the face's images, and the performance of all methods decreases largely with outdoor-illumination. The analyzed methods are robust to inaccurate alignment, face occlusions, and variations in expressions, to a large degree. LBP-based methods are an excellent election if we need real-time operation as well as high recognition rates.
Highlights
Many different face-recognition approaches have been developed in the last few years [1,2,3,4], ranging from classical Eigenspace-based methods, to sophisticated systems based on thermal’s information, highresolution images, or 3D models
In the experiments we considered the best working variants of each method (H, GJD-BC, SD, and ERCF), according to the results obtained in LFW
For the evaluation of ERCF, we trained a system using the implementation of the author of ERCF and the same parameters used to obtain the results presented in [15], which were obtained by a direct communication with the authors of the LFW database
Summary
Many different face-recognition approaches have been developed in the last few years [1,2,3,4], ranging from classical Eigenspace-based methods (see, e.g., eigenfaces [5]), to sophisticated systems based on thermal’s information, highresolution images, or 3D models (see, e.g., [4, 6, 7]). Some timedemanding applications, such as searching faces in nonannotated or partially annotated databases (i.e., news databases, the Internet, etc.) and HRI (Human-Robot Interaction), impose extra requirements of real-time operation, just one image per person and fully on-line operation (no off-line enrollment), which are difficult to achieve. In this general context, the aim of this article is to carry out a comparative study of face-recognition methods by considering these requirements. We want to consider standard 2D images, and not high-resolution, 3D or thermal images that are not always available and that can slow down the recognition process; (iv) unconstrained
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
