DocumentCode :
3263652
Title :
Motion blur analysis based on image segmentation and blind deconvolution
Author :
Xing, Chao ; Li, Yanjun ; Zhang, Ke
Author_Institution :
Sch. of Astronaut., Northwestern Polytech. Univ., Xi´´an, China
Volume :
4
fYear :
2010
fDate :
16-18 Oct. 2010
Firstpage :
1515
Lastpage :
1519
Abstract :
The problem of blurring caused by object motion in a gray level image is analyzed, and an algorithm combining image segmentation and blind deconvolution based on statistical features of objects and background is introduced to estimate visual motion and restore the image. Regions consisting certain geometrical information of pixels are regarded as suspected moving objects and segmented on the base of directional derivative of the image. Simple connected regions are selected by the use of mathematical morphological algorithm and level set method. Convolution kernels of regions larger than a given threshold are inferred through ensemble learning, and blurred regions can be restored individually. Radon transform is adopted to determine motion patterns of objects. Experimental results show the effectiveness of the algorithm for visual motion estimation and deblurring in a gray level image.
Keywords :
Radon transforms; deconvolution; image restoration; image segmentation; motion compensation; Radon transform; blind deconvolution; gray level image; image directional derivative; image restoration; image segmentation; level set method; motion blur analysis; motion deblurring; visual motion estimation; Algorithm design and analysis; Deconvolution; Image restoration; Image segmentation; Kernel; Motion segmentation; Pixel; Level set method; Motion deblurring; Radon transform; Visual motion estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image and Signal Processing (CISP), 2010 3rd International Congress on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6513-2
Type :
conf
DOI :
10.1109/CISP.2010.5647166
Filename :
5647166
Link To Document :
بازگشت