Experimental Approach for Human Perception Based Image Quality Assessment

Abstract. The term ‘image quality’ is a subject notion so it is difficult to quantify. However, it can be reasonably quantified by using statistical and psychophysical approaches. Furthermore, it is also possible to model the human perception of image quality. In this paper, large scale psychophysical experiments including pair comparison and categorical judgment were carried out to judge the perception of image quality of photographic images. The evaluation of both image difference and absolute quality was also carried out. Test images were generated by rendering the eight selected original images according to the change of lightness, chroma, contrast, sharpness and noise attributes. Total number of 288 images were used as test images. The experimental results were used to calculate z-scores and colour difference threshold to verify the optimum level for each transform function. User preferred image content can be provided to entertainment, education, etc. when using the result of the study.