计算机辅助的国画真伪鉴别研究  

COMPUTER-AIDED AUTHENTICATION OF TRADITIONAL CHINESE PAINTING

作　　者：关晓惠[1] 潘纲[1] 吴朝晖[1] 吴敢[2] 

机构地区：[1]浙江大学计算机学院,浙江杭州310027 [2]中国美术学院中国书画鉴赏中心,浙江杭州310002

出　　处：《计算机应用与软件》2007年第4期103-105,144,共4页Computer Applications and Software

摘　　要：中国画的真伪鉴别一直是困扰书画界的难题。传统的完全依赖专家的经验性鉴定方式主要缺点是主观性太强,对于争议的作品难以有令人信服的客观证据。近年来,随着模式识别与计算机视觉技术的快速发展,基于视觉的计算机辅助中国画真伪鉴别正成为学术界的研究热点,它将为专家的经验性鉴定寻找科学的、客观的量化指标进行有益的探索。首先对中国画真伪鉴别的现状进行阐述,然后根据中国画中的三类不同的鉴别对象,分别对相关的视觉鉴别技术进行了综述。Anti-forgery of the traditional Chinese painting is a challenging problem. The traditional authentication method is strongly dependent on the experts＇ empirical knowledge,which is usually lack of objective and convincing proofs. Recently,with the rapid development of computer vision and pattern recognition, vision - based computer - aided authentication of the traditional Chinese painting is becoming attractive ,whose goal is to find the scientific objective and quantitative measurements to help experts＇ authentication work. In this paper we firstly give a brief introduction about the current methods for traditional Chinese painting authentication. Then we survey the related vision techniques for detecting forgery of traditional Chinese painting.

关 键 词：中国画真伪鉴别 印鉴鉴别 书法鉴别 书画赝品 

分 类 号：TP391.72[自动化与计算机技术—计算机应用技术]