DocumentCode :
3271370
Title :
An efficient blind method for image quality measurement
Author :
Wu, Shiqian ; Xie, Shoulie
Author_Institution :
Inst. for Infocomm Res., A*STAR (Agency for Sci., Technol. & Res.), Singapore, Singapore
fYear :
2009
fDate :
8-10 Dec. 2009
Firstpage :
1
Lastpage :
5
Abstract :
This paper presents an efficient blind method for image quality measurement. The key idea is to characterize image quality in terms of image sharpness while the sharpness is considered as blurring. The blur parameter is estimated using sharp edges in the underlying image. To improve the system efficiency, a criterion for edge sharpness is proposed and only the sharpest edges are selected for extraction of line spread function (LSF). The effect of nearby edges on LSF is analyzed, and two constrains are presented to select appropriate LSFs. The experimental results demonstrate that the performance of the proposed method is comparable to the method in, but the speed is much fast. This paradigm can be served as blind image quality evaluation for automatic vision-based applications.
Keywords :
blind source separation; computer vision; edge detection; parameter estimation; automatic vision-based applications; blind image quality evaluation; blur parameter estimation; edge sharpness; image quality measurement; image sharpness; line spread function; Image edge detection; Image quality; Infrared detectors; Infrared image sensors; Low pass filters; Noise level; Noise measurement; Paper technology; Parameter estimation; Ultrasonic variables measurement; Blind image quality evaluation; blur model; edge detection; edge sharpness; line spread function;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information, Communications and Signal Processing, 2009. ICICS 2009. 7th International Conference on
Conference_Location :
Macau
Print_ISBN :
978-1-4244-4656-8
Electronic_ISBN :
978-1-4244-4657-5
Type :
conf
DOI :
10.1109/ICICS.2009.5397656
Filename :
5397656
Link To Document :
بازگشت