Local image descriptor based on spectral embedding. Issue 2 (1st April 2015)

• Record Type: Journal Article
• Authors: Yan, Pu; Tang, Jun; Zhu, Ming; Liang, Dong
• Is Part Of: IET computer vision. Volume 9:Issue 2(2015)
• Page Start: 278
• Page End: 289
• Publication Date: 2015-04-01
• Subjects: image processing -- graph theory; local image descriptor -- spectral embedding -- line graph spectra -- image edge -- image corner -- edge point -- big curvature -- noise robustness -- rotation invariant image descriptor -- linear intensity change -- image rotation -- image blurring -- viewpoint change -- illumination change -- JPEG compression; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2014.0124
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : This study presents a local image descriptor based on spectral embedding. Specifically, the spectra of line graph are used to represent image edges, corners and edge points with big curvature. The authors theoretically analyse and experimentally verify that the spectra of line graph are robust to noise and are invariant to rotation and linear intensity changes. Based on such a fact, some local image descriptors are constructed using the spectra of line graph. Comparative experiments demonstrate the effectiveness of the proposed descriptor and its superiority to some state‐of‐the‐art descriptors under image rotation, image blur, viewpoint change, illumination change, JPEG compression and noise.