Face recognition based on texture information and geodesic distance approximations between multivariate normal distributions

Soldera, J and Dodson, CTJ and Scharkanski, J (2018) Face recognition based on texture information and geodesic distance approximations between multivariate normal distributions. Measurement Science and Technology, 29 (11). pp. 1-9. ISSN ISSN: 1361-6501

[thumbnail of Soldera_2018_Meas._Sci._Technol._29_114001.pdf] Text
Soldera_2018_Meas._Sci._Technol._29_114001.pdf

Download (678kB)

Abstract

Geodesic distance is a natural dissimilarity measure between probability distributions of a specific type, and can be used to discriminate texture in image-based measurements. Furthermore, since there is no known closed-form solution for the geodesic distance between general multivariate normal distributions, we propose two efficient approximations to be used as texture dissimilarity metrics in the context of face recognition. A novel face recognition approach based on texture discrimination in high-resolution color face images is proposed, unlike the typical appearance-based approach that relies on low-resolution grayscale face images. In our face recognition approach, sparse facial features are extracted using predefined landmark topologies, that identify discriminative image locations on the face images. Given this landmark topology, the dissimilarity between distinct face images are scored in terms of the dissimilarities between their corresponding face landmarks, and the texture in each one of these landmarks is represented by multivariate normal distributions, expressing the color distribution in the vicinity of each landmark location. The classification of new face image samples occurs by determining the face image sample in the training set which minimizes the dissimilarity score, using the nearest neighbor rule. The proposed face recognition method was compared to methods representative of the state-of-the-art, using color or grayscale face images, and presented higher recognition rates. Moreover, the proposed texture dissimilarity metric also is efficient in general texture discrimination (e.g., texture recognition of material images), as our experiments suggest.

Item Type: Article
Additional Information: This is the final enlarged journal version of a contribution at an IEEE Conference IEEE Xplore: 18 January 2018
Uncontrolled Keywords: geodesic distance, approximations, multivariate normal distribution, face recognition, sparse features
Subjects: MSC 2010, the AMS's Mathematics Subject Classification > 53 Differential geometry
MSC 2010, the AMS's Mathematics Subject Classification > 62 Statistics
Depositing User: Prof CTJ Dodson
Date Deposited: 21 Oct 2018 09:02
Last Modified: 21 Oct 2018 09:02
URI: https://eprints.maths.manchester.ac.uk/id/eprint/2669

Actions (login required)

View Item View Item