No-reference method for image effective bandwidth estimation

Image evaluation and quality measurements are fundamental components in all image processing applications and techniques. Recently, a no-reference perceptual blur metrics (PBM) was suggested for numerical evaluation of blur effects. The method is based on computing the intensity variations between neighboring pixels of the input image before and after low-pass filtering. The method was proved to demonstrate a very good correlation between the quantitative measure it provides and visual evaluation of perceptual image quality. However, this quantitative image blurriness measure has no intuitive meaning and has no association with conventionally accepted imaging system design parameters such as, for instance, image bandwidth. In this paper, we suggest an extended modification of this PBM-method that provides such a direct association and allows evaluation image in terms of the image efficient bandwidth. To this end we apply the PBM-method to a series of test pseudo-random images with uniform spectrum of different spread within the image base-band defined by the image sampling rate and map the image blur measurement results obtained for this set of test images to corresponding measures of their bandwidths. In this way we obtain a new image feature, which provides evaluation of image in terms of the image effective bandwidth measured in fractions, from 0 to 1, of the image base-band. In addition, we also show that the effective bandwidth measure provides a good estimation for the potential JPEG encoder compression rate, which allows one to choose the best compression quality for a requested compressed image size.