Stimulus Synthesis for Efficient Evaluation and Refinement of
Perceptual Image Quality Metrics
Appears in
Proc. SPIE Conf on Human Vision and Electronic Imaging IX
Vol. 5292, January 2004.
© Society for Photo-optical Instrumentation Engineers.
We propose a methodology for comparing and refining perceptual
image quality metrics based on synthetic images that are optimized
to best differentiate two candidate quality metrics. We start from
an initial distorted image and iteratively search for the
best/worst images in terms of one metric while constraining the
value of the other to remain fixed. We then repeat this, reversing
the roles of the two metrics. Subjective test on the quality of
pairs of these images generated at different initial distortion
levels provides a strong indication of the relative strength and
weaknesses of the metrics being compared. This methodology also
provides an efficient way to further refine the definition of an
image quality metric.
Reprint (1.06M, pdf) | Other Online Publications