Covariance descriptors on a Gaussian manifold and their application to image set classification. (November 2020)

• Record Type: Journal Article
• Authors: Chen, Kai-Xuan; Ren, Jie-Yi; Wu, Xiao-Jun; Kittler, Josef
• Is Part Of: Pattern recognition. Volume 107(2020:Nov.)
• Publication Date: 2020-11
• Subjects: Covariance descriptors -- Riemannian local difference vector -- Riemannian covariance descriptors -- Image set classification; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107463
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Characterizing the similarities between the regions that contain more comprehensive information than pixels. Presenting two methods for computing Riemannian local difference vector on Gaussian manifold (RieLDV-G) and using RieLDV-G to define deviation. Providing a novel framework for computing covariance on Gaussian manifold and generating the proposed Riemannian covariance descriptors (RieCovDs). Abstract: Covariance descriptors (CovDs) for image set classification have been widely studied recently. Different from the conventional CovDs, which describe similarities between pixels at different locations, we focus more on similarities between regions that convey more comprehensive information. In this paper, we extract pixel-wise features of image regions and represent them by Gaussian models. We extend the conventional covariance computation onto a special type of Riemannian manifold, namely a Gaussian manifold, so that it is applicable to our image set data representation provided in terms of Gaussian models. We present two methods to calculate a Riemannian local difference vector on the Gaussian manifold (RieLDV-G) and generate our proposed Riemannian covariance descriptors (RieCovDs) using the resulting RieLDV-G. By measuring the recognition accuracy achieved on benchmarking datasets, we demonstrate experimentally the superior performance of our proposed RieCovDs descriptors, as compared with state-of-the-art methods. ( The code is available at: https://github.com/Kai-Xuan/RiemannianCovDs )