Title :
Analysis and Design of No-Reference Image Quality Assessment
Author :
Tian, Yuan ; Zhu, Ming ; Wang, Ligong
Author_Institution :
Changchun Inst. of Opt., Chinese Acad. of Sci. Changchun, Changchun
Abstract :
No-reference (NR) image quality assessment (IQA) seeks to assign quality scores that are consistent with human perception but without an explicit comparison with the reference image. Unfortunately, the field of NR IQA has been largely unexplored. The basic problems in NR IQA are discussed in this paper. And several methods used in NR IQA are explained and analyzed. Finally, an overall NR IQA method is designed. It should be a synthetical index, which applying fuzzy measures and fuzzy integrals, incorporating human vision system (HVS) characteristics and adhering to the philosophy of quantifying quality through blind distortion measurement.
Keywords :
fuzzy set theory; image processing; blind distortion measurement; fuzzy integrals; fuzzy measures; human perception; human vision system; no-reference image quality assessment; synthetical index; Design methodology; Distortion measurement; Fuzzy systems; Humans; Image analysis; Image databases; Image quality; Optical distortion; Physics; Videos; fuzzy measures and fuzzy integrals; human visual system (HVS); image quality assessment (IQA); no-reference (NR); objective method;
Conference_Titel :
MultiMedia and Information Technology, 2008. MMIT '08. International Conference on
Conference_Location :
Three Gorges
Print_ISBN :
978-0-7695-3556-2
DOI :
10.1109/MMIT.2008.171
