A knowledge-aided line network oriented vectorisation method for engineering drawings

Citation
Jq. Song et al., A knowledge-aided line network oriented vectorisation method for engineering drawings, PATTERN A A, 3(2), 2000, pp. 142-152
Citations number
10
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
PATTERN ANALYSIS AND APPLICATIONS
ISSN journal
14337541 → ACNP
Volume
3
Issue
2
Year of publication
2000
Pages
142 - 152
Database
ISI
SICI code
1433-7541(2000)3:2<142:AKLNOV>2.0.ZU;2-C
Abstract
Vectorisation is the foundation in recognising engineering components from paper form drawings. Due re, the complexity of problems and the difficulty of techniques, the vectorisation method relying merely on the image itself cannot get satisfactory results. It. is now widely agreed that the knowledg e must be applied more or less to aid the vectorisation. The capability of the vectorisation method itself should also be thus improved. This paper an alyses the problems of existing vectorisation methods, introduces the compl ete concept of global vectorisation, and proposes a whole new line network oriented global vectorisation method. This method uses global information t o vectorise a line in one step, and carries out the global vectorisation of line networks. Therefore, the problem of separating one line is solved, an d a complex analysis of crossings is avoided. The performance of vectorisat ion is improved clearly. Furthermore, it can vectorise lines in any orienta tions well, and can vectorise a dashed line in one step. Aided by the relat ed knowledge, local details of vectorisation are refined. A performance eva luation compared with other vectorisation methods is also included.