Title
Objective distortion measure for binary text image based on edge line segment similarity.
Abstract
This paper proposes a new approach to measure the distortion introduced by changing individual edge pixels in binary text images. The approach considers not only how many pixels are changed but also where the pixels are changed and how the flipping affects the overall shape formed by the edge line. Similarities between the edge line segments in the original and distorted image are compared to measure the distortion. Subjective testing shows that the new distortion measure correlates well with human visual perception.
Year
DOI
Venue
2007
10.1109/TIP.2007.896619
IEEE Transactions on Image Processing
Keywords
Field
DocType
distorted image,edge line segment similarity,individual edge pixel,subjective testing,objective distortion measure,overall shape,new distortion measure,edge line segment,binary text image,edge line,new approach,human visual perception,artificial intelligence,computer graphics,testing,visual perception,image segmentation,image processing,pixel,image resolution,shape,algorithms,distortion,psnr
Computer vision,Line segment,Pattern recognition,Edge detection,Binary image,Image quality,Image segmentation,Artificial intelligence,Pixel,Image resolution,Distortion,Mathematics
Journal
Volume
Issue
ISSN
16
6
1057-7149
Citations 
PageRank 
References 
9
0.56
7
Authors
2
Name
Order
Citations
PageRank
Jun Cheng121420.65
A. C. Kot225820.69