engleski

New Image Quality Measure Based on Wavelets

In our paper we present innovative approach to objective quality evaluation that could be computed using mean difference between original and tested image in different wavelet subbands. DWT subband decomposition properties are similar to human visual system (HVS) characteristics facilitating integration of DWT into image quality evaluation. DWT decomposition is done with multiresolution analysis of a signal that allows us to decompose a signal into approximation and detail subbands. DWT coefficients were computed using reverse biorthogonal spline wavelet filter banks. Coefficients for HH subband in level 2 are used to compute new image quality measure (IQM). IQM is defined as difference between HH level 2 coefficients of original and degraded image.

Discrete wavelet transform; MSE; SSIM; PSNR; image quality measure; DMOS

nije evidentirano