Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2015, Vol. 51 ›› Issue (6): 1008-1016.DOI: 10.13209/j.0479-8023.2015.086

Previous Articles     Next Articles

Study on Key Problems for Plane Geometric Diagram Retrieval

FU Songping1, LÜ Xiaoqing1, LIU Lu1, FENG Tianxiao1, LI Keqiang1, TANG Zhi1,2   

  1. 1. Institute of Computer Science & Technology, Peking University, Beijing 100080
     2. State Key Laboratory of Digital Publishing Technology (Peking University Founder Group), Beijing 100871
  • Received:2014-09-20 Online:2015-11-20 Published:2015-11-20
  • Contact: LÜ Xiaoqing, E-mail: lvxiaoqing(at)pku.edu.cn

平面几何图形检索的关键问题研究

符松平1, 吕肖庆1, 刘璐1, 冯天骁1, 李克强1, 汤帜1,2   

  1. 1. 北京大学计算机科学技术研究所, 北京 100080
    2. 数字出版技术国家重点实验室(北大方正集团有限公司), 北京 100871
  • 通讯作者: 吕肖庆, E-mail: lvxiaoqing(at)pku.edu.cn
  • 基金资助:
    国家自然科学基金(61472014, 61300061)资助

Abstract:

Based on the study of retrieving plane geometric figures (PGFs) in the area of computer aided instruction, a feasible solution for PGF retrieval is proposed. The authors focus on several challenging tasks such as sketch beautification, geometric primitive detection, salience analysis of the overlapped primitives, structural
relationship description between two geometric primitives, and figure similarity computing. Several algorithms are presented especially on layout description and complex shape matching. The PGFs are applied directly to content retrieval and compensate for the weaknesses in describing the query intentions using keyword-based search. Experimental results demonstrate the feasibility and significant performance of the proposed retrieval algorithm.

Key words: sketch beautification, geometric primitives detection, salience analysis of the overlapped primitives, structural relationship description between two geometric primitives, shape matching, image retrieval, plane geometric figures

摘要:

基于计算机辅助教学领域中平面几何图形的识别和检索研究, 提出一套可行的完整解决方案,并对手绘图美化、基本图元检测、显著性分析、位置关系描述和匹配度计算等关键问题进行分析。在深入分析几何图各级特征的同时, 提出具有较强针对性的布局关系描述和复杂图形匹配的多种算法, 使得几何图形最终得以直接用于内容检索, 弥补了基于关键字检索技术在描述查询意图方面的不足。实验结果表明, 本文提出的解决方案不仅可行, 而且具有较高的准确度。

关键词: 手绘图美化, 基本图元检测, 交叠图元显著性, 双图元结构描述子, 图形匹配, 图像检索, 平面几何图形

CLC Number: