{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/contrast-and-visual-saliency-similarity","title":"Contrast and visual saliency similarity-induced index for assessing image quality","arxiv_id":"1708.06616","date":"2017-08-22","proceeding":null,"authors":["Huizhen Jia","Lu Zhang","Tonghan Wang"],"abstract":"Image quality that is consistent with human opinion is assessed by a\nperceptual image quality assessment (IQA) that defines/utilizes a computational\nmodel. A good model should take effectiveness and efficiency into\nconsideration, but most of the previously proposed IQA models do not\nsimultaneously consider these factors. Therefore, this study attempts to\ndevelop an effective and efficient IQA metric. Contrast is an inherent visual\nattribute that indicates image quality, and visual saliency (VS) is a quality\nthat attracts the attention of human beings. The proposed model utilized these\ntwo features to characterize the image local quality. After obtaining the local\ncontrast quality map and the global VS quality map, we added the weighted\nstandard deviation of the previous two quality maps together to yield the final\nquality score. The experimental results for three benchmark databases (LIVE,\nTID2008, and CSIQ) demonstrated that our model performs the best in terms of a\ncorrelation with the human judgment of visual quality. Furthermore, compared\nwith competing IQA models, this proposed model is more efficient.","url_abs":"http://arxiv.org/abs/1708.06616v3","url_pdf":"http://arxiv.org/pdf/1708.06616v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"full-reference-image-quality-assessment","task_name":"Full reference image quality assessment"},{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/full-reference-image-quality-assessment-on","task":"Full reference image quality assessment","dataset":"TID2008","model":"IQA Metric","rank_in_archive_order":3,"of":13,"metrics":{"PLCC":"0.8961","SRCC":"0.9001"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}