Computationally efficient image deblurring using low rank image approximation and its GPU implementation

详细信息    查看全文

• 作者：Chih-Hsiang Chang ; Nasser Kehtarnavaz
• 关键词：Computationally efficient image deblurring ; GPU implementation ; Low rank image approximation
• 刊名：Journal of Real-Time Image Processing
• 出版年：2016
• 出版时间：October 2016
• 年：2016
• 卷：12
• 期：3
• 页码：567-573
• 全文大小：1,081 KB
• 刊物类别：Computer Science
• 刊物主题：Image Processing and Computer Vision
  Multimedia Information Systems
  Computer Graphics
  Pattern Recognition
  Signal,Image and Speech Processing
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1861-8219
• 卷排序：12

文摘

This paper presents a computationally efficient technique for reduction of blur caused by handshakes in images captured by mobile devices. This technique uses a short-exposure or a low-exposure image that is captured at the same time a normal or auto-exposure image is captured. The short-exposure image is enhanced by utilizing low rank image approximation of the auto-exposure image without requiring any user specified parameters. Based on the three quantitative measures of image quality, it is shown that this technique outperforms similar techniques used for image deblurring while it also offers computational efficiency. A GPU implementation of this technique is also reported.