期刊名称：Signal & Image Processing : An International Journal (SIPIJ)
印刷版ISSN：2229-3922
电子版ISSN：0976-710X
出版年度：2012
卷号：3
期号：5
页码：41
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Image quality assessment (IQA) evaluates the quality of an image by computing the difference between thereference and distorted images. This paper proposes an image quality metric (IQM) that uses the motifscan. Since edges often contain much information on an image and the human visual system is highlyadapted for extracting structural information from a scene, we propose a new IQM comparing thesimilarity of 3×3 block motif scans between the reference and distorted images, where the center of theblock is located at edge pixel. A 3×3 block is divided into four overlapping 2×2 grids with the center pixellocated at four different corners. The modified versions of the proposed IQM using the uniform andGaussian weights are also proposed. Experiments with LIVE database for five different distortion types oftest images show that the proposed metric gives better performance than the conventional IQMs.
