Abstract
This paper focuses on the use of Gaussian Mixture models (GMM) for 3D face verification. A special interest is taken in practical aspects of 3D face verification systems, where all steps of the verification procedure need to be automated and no meta-data, such as pre-annotated eye/nose/mouth positions, is available to the system. In such settings the performance of the verification system correlates heavily with the performance of the employed alignment (i.e., geometric normalization) procedure. We show that popular holistic as well as local recognition techniques, such as principal component analysis (PCA), or Scale-invariant feature transform (SIFT)-based methods considerably deteriorate in their performance when an “imperfect” geometric normalization procedure is used to align the 3D face scans and that in these situations GMMs should be preferred. Moreover, several possibilities to improve the performance and robustness of the classical GMM framework are presented and evaluated: i) explicit inclusion of spatial information, during the GMM construction procedure, ii) implicit inclusion of spatial information during the GMM construction procedure and iii) on-line evaluation and possible rejection of local feature vectors based on their likelihood. We successfully demonstrate the feasibility of the proposed modifications on the Face Recognition Grand Challenge data set.
Highlights
Face recognition (FR) technology exhibits some attractive properties such as high user acceptance, non‐ intrusiveness of the acquisition procedure and commer‐ cial potential in a diverse range of applications in both the private as well as the public sector
One of these solu‐ tions relies on different capture techniques to replace the still‐image recognition procedure with rec‐ ognition techniques based on video data, infrared images or 3D images
Systems based on local feature vectors and gen‐ erative statistical models, such as GMMs demonstrated their effectiveness for 3D face recognition [5, 6]
Summary
Face recognition (FR) technology exhibits some attractive properties such as high user acceptance, non‐ intrusiveness of the acquisition procedure and commer‐ cial potential in a diverse range of applications in both the private as well as the public sector. Systems based on local feature vectors and gen‐ erative statistical models, such as GMMs demonstrated their effectiveness for 3D face recognition [5, 6]. GMM‐based sys‐ tems treat data (i.e., feature vectors) as independently and identically distributed (i.i.d.) observations and, present facial data in the form of a number of orderless blocks This characteristic is reflected in good robustness to imperfect face alignment, pose changes, occlusions and expression variations.. The spatial rela‐ tionships between the local feature vectors are lost, since correlations among adjacent observations are discarded This loss of information on the spatial structure of the face data often results in degraded recognition perform‐ ance.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
