Paper
12 January 2012 A two-stage method to extract the blurred area
Xianyong Fang, Hao Wu, Zhongbiao Wu, Bin Luo, Biao He
Author Affiliations +
Abstract
The image may be partially blurred because of defocus, shaking camera or moving object. In this paper, we introduce a novel method to extract the blurred area automatically, which mainly consists of two stages: coarse detection and fine extraction. In the coarse detection, we proposed a block-based blurred/sharp area detection algorithm which roughly divides the image into blurred, sharp and undefined blocks. Both the spatial gradient statistics and the frequential power spectrum are used as blur metrics in the algorithm. For the fine extraction, we introduce an improved lazy snapping which takes blurred and sharp blocks of the coarse detection as the seeds for automatic lazy snapping and thus extracts the blurred area automatically. Experimental results prove that the efficiency of the proposed method.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xianyong Fang, Hao Wu, Zhongbiao Wu, Bin Luo, and Biao He "A two-stage method to extract the blurred area", Proc. SPIE 8350, Fourth International Conference on Machine Vision (ICMV 2011): Computer Vision and Image Analysis; Pattern Recognition and Basic Technologies, 83501F (12 January 2012); https://doi.org/10.1117/12.921793
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Detection and tracking algorithms

Image processing algorithms and systems

Linear filtering

Picosecond phenomena

Cameras

Image analysis

RELATED CONTENT

Wound image analysis system for diabetics
Proceedings of SPIE (March 13 2013)
Statistical pattern recognition for rock joint images
Proceedings of SPIE (November 03 2005)
Real-time face tracking
Proceedings of SPIE (October 06 1998)
Corn tassel detection based on image processing
Proceedings of SPIE (November 15 2011)

Back to Top