Evaluating Blind Image Quality Using RBF Neural Network
Keywords:Blind image quality assessment, Radial bias function (RBF) neural network, Multivariate Gaussian
Blind Image Quality Assessment (BIQA) methods are the most part feeling mindful. The BIQA method learns regression models from preparing images with human subjective scores to predict the perceptual nature of test images. The general quality of image and the nature of every image patches are measured by normal pooling. By coordinating the components of normal picture measurements got from different signs, we take a multivariate Gaussian model of picture patches from an accumulation of unblemished regular pictures. The proposed radial bias function neural network method is used to evaluate the quality of images and this method represents the structure of picture distortions with flexibility.
 A. K. Moorthy and A. C. Bovik, “A two-step framework for constructing blind image indices,” IEEE Signal Process. Lett., vol. 17, no. 5, May 2010
 M. A. Saad, A. C. Bovik, and C. Charrier, “A DCT statistics-based blind image quality index,” IEEE Signal Process. Lett., vol. 17, no. 6, Jun 2010.
 P. Ye, J. Kumar, L. Kang, and D. Doermann, “Unsupervised feature learning framework for no-reference image quality assessment,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2012.
 D. J. Field, “Relations between the statistics of natural images and the response properties of cortical cells,” J. Opt. Soc. Amer. A, vol. 4, no. 12, Dec. 1987.
 A. K. Moorthy and A. C. Bovik, “Visual importance pooling for image quality assessment,” IEEE J. Sel. Topics Signal Process., vol. 3, no. 2, Apr. 2009
 R. V. Babu, S. Suresh, and A. Perkis, “No-reference JPEG-image quality assessment using GAP-RBF,” Signal Process., vol. 87, no. 6, Jun. 2007.
 Lei Zhang and Alan C. Bovik, “A Feature-Enriched Completely Blind Image Quality Evaluator,” IEEE Trans. Image Process., vol. 24, no. 8, August.2015.