21 July 2017 A blur-invariant local feature for motion blurred image matching
Author Affiliations +
Proceedings Volume 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017); 104201E (2017) https://doi.org/10.1117/12.2281710
Event: Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, Hong Kong, China
Abstract
Image matching between a blurred (caused by camera motion, out of focus, etc.) image and a non-blurred image is a critical task for many image/video applications. However, most of the existing local feature schemes fail to achieve this work. This paper presents a blur-invariant descriptor and a novel local feature scheme including the descriptor and the interest point detector based on moment symmetry – the authors’ previous work. The descriptor is based on a new concept - center peak moment-like element (CPME) which is robust to blur and boundary effect. Then by constructing CPMEs, the descriptor is also distinctive and suitable for image matching. Experimental results show our scheme outperforms state of the art methods for blurred image matching
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Qiang Tong, Terumasa Aoki, "A blur-invariant local feature for motion blurred image matching", Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104201E (21 July 2017); doi: 10.1117/12.2281710; https://doi.org/10.1117/12.2281710
PROCEEDINGS
6 PAGES


SHARE
Back to Top