Paper Info
Title
No-Reference Quality Assessment For Jpeg2000 Compressed Images.
Abstract
No-Reference quality assessment is a relatively new topic and has been attracting more and more attention in recent years. Due to the limited understanding of the human vision system, most of the existing methods focus Oil measuring to what extent the image has been distorted. In this paper, by viewing all edge points in JPEG2000 compressed images as 'distorted' or 'un-distorted', we propose using principal component analysis (PCA) to extract the local feature of a given edge point, which indicates both blurring and ringing. We also propose using the probabilities of the given edge point being 'distorted' and 'un-distorted' to model the local distortion metric, which is straight forward and can be easily applied to any type or local feature. Experimental results demonstrate the effectiveness of our scheme.
Year
DOI
Venue
2004
10.1109/ICIP.2004.1421880
ICIP: 2004 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1- 5
Keywords
Field
DocType
principal component analysis,data compression
Computer vision,Machine vision,Pattern recognition,Ringing,Computer science,Image coding,Artificial intelligence,JPEG 2000,Data compression,Distortion,Principal component analysis
Conference
ISSN
Citations 
PageRank 
1522-4880
22
2.31
References 
Authors
5
4
Name
Order
Citations
PageRank
Hanghang Tong13560202.37
Mingjing Li23076192.39
Hong-Jiang ZHANG3173781393.22
Changshui Zhang45506323.40