Multiscale geometric analysis based image quality assessment

In reduced-reference (RR) image quality assessment (IQA), the visual quality of distorted images is evaluated with only partial information extracted from original images. In the proposed framework, MGA (multiscale geometric analysis) is utilized to decompose images and then extract features to mimic the multi-channel structure of HVS based on hybrid wavelets and directional filter banks (HWD) transform. Different transforms capture different types of image geometric information. CSF is applied to weight coefficients obtained by MGA to simulate the appearance of images to observers by taking into account many of the nonlinearities inherent in HVS. JND is finally introduced to produce a noticeable variation in sensory experience. Experimental results illustrate that even with low data rate; the proposed framework has still good consistency with the subjective perception.