基于头饰特征的唐卡标注和检索  

Thangka Annotation and Retrieval Based on Headdress Features

作　　者：毕学慧[1] 刘华明[1] 王维兰[2] 

机构地区：[1]阜阳师范学院计算机与信息学院,阜阳236000 [2]西北民族大学计算机科学与信息工程学院,兰州7300302

出　　处：《计算机科学》2014年第2期312-316,共5页Computer Science

基　　金：国家自然科学基金项目(60875006);安徽省教育厅自然科学基金项目(KJ2013B195;KJ2012B131);阜阳师范学院自然科学基金项目(2011FSKJ04)资助

摘　　要：通过提取唐卡头饰特征实现自动分类的主要步骤有:通过人机交互选择头饰区域,采用迭代与基于RGB的算法分割,预处理分割结果,获取头饰的初始分割图;提取初始分割图的欧拉数特征以分出头冠;提取初始分割图外轮廓的傅里叶描述子特征,根据特征值到各自聚类中心的距离来分类发髻和僧帽。唐卡头饰自动分类的实现,提高了分类效率,满足了头饰自动语义标注和语义检索的需要。根据应用需求,设计的唐卡检索系统不仅可以实现基于文本、内容和语义的检索,还提高了检索的精确度。Automatic classification can be done by extracting Thangka headdress features, the main steps：1） select the headdress region through human-computer interaction and obtain initial segmentation image by preprocessing the seg- mentation result which is segmented through iterative segmentation or segmentation algorithm based on RGB; 2） sepa- rate the crown by the Euler number which is extracted from the initial segmentation image; 3） extract Fourier descrip- tors from out contour of the initial segmentation image, separate hairpin or monk hat through the distance between the feature and each cluster center. The realization of headdress automatic classification can improve the classification effi- cieney and meet the needs of automatic semantic annotation and semantic retrieval. According to the demand of applica- tion, we designed a retrieval system, which can realize retrieval based on text, content and semantics, and improve the accuracy of retrieval.

关 键 词：唐卡检索 头饰分类 语义标注 分级检索系统 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]