Title
A no-reference quality metric for measuring image blur
Abstract
In this paper, a method for measuring the perceptual quality of bluffed images has been proposed. Here, the amount of image blur. is characterized by the average extent of edges in the image, or more specifically the average extent of the slope's spread of an edge in the opposing gradients' directions. The effectiveness of such method is validated using subjective tests on blurred images, including JPEG-2000 coded images, and the experimental results show that the proposed method can provide results that correlate relatively well with human subjective ratings.
Year
DOI
Venue
2003
10.1109/ISSPA.2003.1224741
SEVENTH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, VOL 1, PROCEEDINGS
Keywords
Field
DocType
transform coding,psnr,testing,digital images,visual perception,data compression,image analysis,image quality,jpeg 2000,edge detection,joint photographic experts group,signal processing
Computer vision,Image gradient,Pattern recognition,Image texture,Computer science,Binary image,Image quality,Image processing,Artificial intelligence,Image restoration,Digital image processing,Standard test image
Conference
Citations 
PageRank 
References 
49
2.63
7
Authors
8
Name
Order
Citations
PageRank
eeping ong11449.18
Weisi Lin25366280.14
Zhongkang Lu357746.90
Xiaokang Yang43581238.09
susu yao555942.48
feng pan61177.66
lijun jiang7492.63
fulvio moschetti88810.40