Title: Automatic Rule Acquisition for Self-Adapting Object Recognition in Engineering Drawings
Abstract: Through analyzing the graphics composition characteristics of objects in engineering drawings, this paper devises a kind of object feature set suitable for recognition, and then proposes a new approach that will automatically extract the object feature sets and convert the features into the recognition rules. This paper also proposes to employ this rule acquisition method in recognition systems, making the rules of one system can be generated and adjusted conveniently, so it is much easier for the systems adapting to new types of engineering objects. This method has been experimented in one architectural drawing analysis system and shown to embody higher efficiency and practicability.
Publication Year: 2003
Publication Date: 2003-01-01
Language: en
Type: article
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot