Paper Details: Downloads: 610
Serial Number: P1150628001
Title: An Image Quality Assessment Technique Based on Visual Regions of Interest Weighted Structural Similarity
Authors: D.Venkata Rao, N.Sudhakar, B.Ravindra Babu, L.Pratap Reddy
Abstract: Measurement of visual quality is of fundamental importance to numerous image and video processing applications. The goal of quality assessment research is to design algorithms that can automatically assess the quality of images. This paper introduces an image quality index Visual region of interest Weighted Structural Similarity (VroiWSSI). The index integrates the notion of Visual regions of interest with the measurement of structural similarity to effectively match with Human Visual System (HVS). The method evaluates the structural similarity between the original image and the distorted image to arrive at structural similarity index in a local region. The indices are then weighted based on the Visual regions of interest characterized by entropy in the local region that emphasizes the texture variance. VroiWSSI of the image is calculated by averaging these weighted indices. Test results show that VroiWSSI correlates well with subjective scores.
Keywords: Visual region of interest Weighted Structural Similarity Index (VroiWSSI), Visual regions of interest, Human Visual System (HVS), Structural similarity, Entropy, Texture variance
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 6
Issue: 2
Submission Date: 4/1/2006 12:00:00 AM
Review Date: 6/1/2006 12:00:00 AM
Publishing Date: 9/1/2006 12:00:00 AM
Article Downloads: 610
Download:

Facebook