Objective color image quality assessment based on Sobel magnitude. Issue 1 (January 2017)

• Record Type: Journal Article
• Authors: Gupta, Savita; Gore, Akshay; Kumar, Satish; Mani, Sneh; Srivastava, P.
• Is Part Of: Signal, image and video processing. Volume 11:Issue 1(2017)
• Page Start: 123
• Page End: 128
• Publication Date: 2017-01
• Subjects: Full reference (FR) -- Perceptual quality -- Image quality assessment (IQA); Signal processing -- Digital techniques -- Periodicals; Image processing -- Digital techniques -- Periodicals; Digital video -- Periodicals; 621.3822
• DOI: 10.1007/s11760-016-0910-9
• Languages: English
• ISSNs: 1863-1703

Abstract

Abstract Image quality assessment algorithms aim to evaluate the perceptual quality of an image by assigning an evaluation score. By comparing the scores, the perceptual similarity or difference between two images can be assessed. In this paper, we present a new full-reference image quality metric method which was developed by combining Sobel magnitude and chrominance information in the YIQ color space. But differing from existing methods, our model incorporates color intensity adaptation to extract and enhance perceptually significant image features. The proposed metrics are tested on three well-known databases available in the literature (TID2013, TID2008, and CSIQ). Experimental results presented to confirm that the proposed metric is an effective and have low computational complexity.