A blur-invariant local feature for motion blurred image matching

Qiang Tong, Terumasa Aoki

研究成果: Conference contribution

抄録

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.

本文言語English
ホスト出版物のタイトルNinth International Conference on Digital Image Processing, ICDIP 2017
編集者Xudong Jiang, Charles M. Falco
出版社SPIE
ISBN(電子版)9781510613041
DOI
出版ステータスPublished - 2017 1月 1
イベント9th International Conference on Digital Image Processing, ICDIP 2017 - Hong Kong, China
継続期間: 2017 5月 192017 5月 22

出版物シリーズ

名前Proceedings of SPIE - The International Society for Optical Engineering
10420
ISSN(印刷版)0277-786X
ISSN(電子版)1996-756X

Other

Other9th International Conference on Digital Image Processing, ICDIP 2017
国/地域China
CityHong Kong
Period17/5/1917/5/22

ASJC Scopus subject areas

  • 電子材料、光学材料、および磁性材料
  • 凝縮系物理学
  • コンピュータ サイエンスの応用
  • 応用数学
  • 電子工学および電気工学

フィンガープリント

「A blur-invariant local feature for motion blurred image matching」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル