Earticle

초록

영어

Blurry images are the bane of many photographers. Although sometimes these images could be retaken in the hope that the next exposure will not be blurred, but frequently they are of some unique event that could only be captured once. The most common cause of blurry images is camera shake. Camera shake means that during the exposure the camera moved. This movement may be very small but still creates blurry images. In this paper, a novel blind-deblurring approach for removing the effect of camera shake from blurry image is proposed. Starting with an image that has been blurred by camera shake, we recover the unknown shape image in two phases: (i) a kernel estimation phase using Radon transform method, and (ii) the shape image recovery based on EM algorithm. Comprehensive comparisons on a number of blurry images show that our approach is not only substantially faster, but it also leads to better deblurring results. Our experimental results are also shown for comparisons. Visually, we find that the restored images are better than those given by the algorithm in other methods from previous works.

목차

Abstract
 1. Introduction
 2. Related Work
 3. Blur Model and Proposed Algorithm
  3.1. Image and Blur Model
  3.2. Blur Kernel Estimation
  3.3. Image Reconstruction
  3.4. Kernel Size Optimization
 4. Experimental Results and Comparisons
 5. Conclusion
 References

키워드

저자

• Quang Thi Nguyen [ Changchun University of Science and Technology – China ]
• Yong Gang Cao [ Changchun University of Science and Technology – China, Changchun Institute of Optics, Fine Mechanics and Physics - Chinese Academy of Sciences - China, ]
• Guang Wen Liu [ Changchun University of Science and Technology – China ]
• Nghia Pham Minh [ Harbin Institute of Technology, China ]
• Van Nhu Le [ Harbin Institute of Technology, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Signal Processing, Image Processing and Pattern Recognition

• 간기

  격월간

• pISSN

  2005-4254

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605