TRANSLATION-, ROTATION- AND SCALE- INVARIANT RECOGNITION OF HAND-DRAWN SYMBOLS IN SCHEMATIC DIAGRAMS

Author:

LEE SEONG-WHAN1,KIM JIN H.2,GROEN FRANS C.A.3

Affiliation:

1. Department of Computer Science, Chungbuk National University, Cheongju, Chungbuk 360–763, Republic of Korea

2. Department of Computer Science, Korea Advanced Institute of Science and Technology, P.O. Box 150, Cheongryang, Seoul 130–650, Republic of Korea

3. Department of Computer Systems, University of Amsterdam, P.O. Box 41882, 1009 DB Amsterdam, The Netherlands

Abstract

In this paper, a model-based scheme for recognizing hand-drawn symbols in schematic diagrams using attributed graph (AG) matching in the absence of any information concerning their pose (translation, rotation and scale) is described. The process of AG matching proceeds as follows. First, an observed AG (AGO) is constructed from single-pixel-width line-representation of an observed symbol. Second, the pose of the AGO is estimated in terms of translation, rotation and scale with respect to the model AGs (AGM s ). The search space is effectively pruned by introducing the concept of control vertex and applying geometrical constraints in an early stage. In this step, a small number of candidate AGM s are selected. Third, correspondences between components of the observed AG after normalization (AGON) and those of the AGMs are found for the given poses. Fourth, distance measures between the AGON and the AGM s are calculated, based upon the correspondences. Finally, the AGON is classified as the AGM with the minimum distance. Experimental results for hand-drawn symbols with and without templates show that using AG matching is very efficient and successful for translation-, rotation- and scale-invariant recognition of hand-drawn symbols in schematic diagrams.

Publisher

World Scientific Pub Co Pte Lt

Subject

Artificial Intelligence,Computer Vision and Pattern Recognition,Software

Cited by 38 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Symbol Detection in Mechanical Engineering Sketches: Experimental Study on Principle Sketches with Synthetic Data Generation and Deep Learning;Applied Sciences;2024-07-12

2. Image format pipeline and instrument diagram recognition method based on deep learning;Biomimetic Intelligence and Robotics;2024-03

3. A Complete Piping Identification Solution for Piping and Instrumentation Diagrams;2023 IEEE International Conference on High Performance Computing & Communications, Data Science & Systems, Smart City & Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys);2023-12-17

4. Action-aware Masking Network with Group-based Attention for Temporal Action Localization;2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2023-01

5. Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos;2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2023-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3