基于知识图谱的肤色检测研究进展分析  

Research progress of skin color detection based on knowledge graoh

作　　者：任香如 万晓霞[1] 单月 刘段 REN Xiangru;WAN Xiaoxia;SHAN Yue;LIU Duan(Research Center of Graphic Communication,Printing and Packaging,Wuhan University,Wuhan 430000,China)

机构地区：[1]武汉大学图像传播与印刷包装研究中心,武汉430000

出　　处：《激光杂志》2023年第3期10-15,共6页Laser Journal

基　　金：国家自然科学基金资助(No.61275172)。

摘　　要：通过知识图谱对肤色检测领域的研究热点和研究现状归纳总结,分析该领域存在问题,并对未来研究进行展望。对Web of Science核心数据库中检索得到的3 472篇相关文献集合,从文献发表量、国家机构合作关系、关键词突现、关键词共现、文献共被引进行可视化分析。结果表明,肤色检测领域研究成果丰富,吸引众多国家、机构及作者研究,但相互间合作较少。研究热点集中在人脸检测、皮肤镜图像处理等方面,神经网络技术的发展也在推进肤色检测的智能化进程。但目前仍面临缺乏标准数据库、算法精度不高与检测成本高昂等局限,未来应进行针对性研究。Based on the knowledge graph,the hot spots and current research status in the field of skin color detection are summarized,the existing problems in this field are analyzed,and the future research is prospected.The 3472 related literatures retrieved from the Web of Science core database were visually analyzed from five aspects,including the number of publications,the cooperation relationship between national institutions,the emergence and co-emergence of keywords,and the co-citation of literatures.The results show that there are rich academic achievements in the field of skin color detection.Many national institutions and authors have studied in this field,but there is little cooperation between them.The research hotpots mainly focus on face detection,dermatology image processing,etc.,and the development of neural network technology is also promoting the intelligent process of skin color detection.However,there are still some limitations such as lack of standard database,low algorithm accuracy and high detection cost.The targeted research should be carried out in the future.

关 键 词：肤色检测 肤色分割 CITESPACE 可视化分析 知识图谱 

分 类 号：TN209[电子电信—物理电子学]