{"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/face-sketch-synthesis-style-similaritya-new","title":"Face Sketch Synthesis Style Similarity:A New Structure Co-occurrence Texture Measure","arxiv_id":"1804.02975","date":"2018-04-09","proceeding":null,"authors":["Deng-Ping Fan","Shengchuan Zhang","Yu-Huan Wu","Ming-Ming Cheng","Bo Ren","Rongrong Ji","Paul L. Rosin"],"abstract":"Existing face sketch synthesis (FSS) similarity measures are sensitive to\nslight image degradation (e.g., noise, blur). However, human perception of the\nsimilarity of two sketches will consider both structure and texture as\nessential factors and is not sensitive to slight (\"pixel-level\") mismatches.\nConsequently, the use of existing similarity measures can lead to better\nalgorithms receiving a lower score than worse algorithms. This unreliable\nevaluation has significantly hindered the development of the FSS field. To\nsolve this problem, we propose a novel and robust style similarity measure\ncalled Scoot-measure (Structure CO-Occurrence Texture Measure), which\nsimultaneously evaluates \"block-level\" spatial structure and co-occurrence\ntexture statistics. In addition, we further propose 4 new meta-measures and\ncreate 2 new datasets to perform a comprehensive evaluation of several\nwidely-used FSS measures on two large databases. Experimental results\ndemonstrate that our measure not only provides a reliable evaluation but also\nachieves significantly improved performance. Specifically, the study indicated\na higher degree (78.8%) of correlation between our measure and human judgment\nthan the best prior measure (58.6%). Our code will be made available.","url_abs":"http://arxiv.org/abs/1804.02975v1","url_pdf":"http://arxiv.org/pdf/1804.02975v1.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":[{"paper_slug":"face-sketch-synthesis-style-similaritya-new","repo_url":"https://github.com/DengPingFan/Scoot","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"face-sketch-synthesis","task_name":"Face Sketch Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}