16 March 2017 Learning moment-based fast local binary descriptor
Author Affiliations +
Abstract
Recently, binary descriptors have attracted significant attention due to their speed and low memory consumption; however, using intensity differences to calculate the binary descriptive vector is not efficient enough. We propose an approach to binary description called POLAR_MOBIL, in which we perform binary tests between geometrical and statistical information using moments in the patch instead of the classical intensity binary test. In addition, we introduce a learning technique used to select an optimized set of binary tests with low correlation and high variance. This approach offers high distinctiveness against affine transformations and appearance changes. An extensive evaluation on well-known benchmark datasets reveals the robustness and the effectiveness of the proposed descriptor, as well as its good performance in terms of low computation complexity when compared with state-of-the-art real-time local descriptors.
© 2017 SPIE and IS&T
Abdelkader Bellarbi, Abdelkader Bellarbi, Nadia Zenati, Nadia Zenati, Samir Otmane, Samir Otmane, Hayet Belghit, Hayet Belghit, } "Learning moment-based fast local binary descriptor," Journal of Electronic Imaging 26(2), 023006 (16 March 2017). https://doi.org/10.1117/1.JEI.26.2.023006 . Submission: Received: 17 August 2016; Accepted: 17 February 2017
Received: 17 August 2016; Accepted: 17 February 2017; Published: 16 March 2017
JOURNAL ARTICLE
11 PAGES


SHARE
RELATED CONTENT

An improved TLD with Harris corner and color moment
Proceedings of SPIE (February 07 2017)
A new corner detecting method based on contourlet transfrom
Proceedings of SPIE (October 29 2009)
Corner detection: splitting method and its optimization methods
Proceedings of SPIE (September 24 1998)
Role of computer vision in augmented virtual reality
Proceedings of SPIE (March 29 1995)
Vision-based natural feature tracking for augmented reality
Proceedings of SPIE (September 04 2002)

Back to Top