대한전기학회:학술대회논문집 (Proceedings of the KIEE Conference)

대한전기학회 (The Korean Institute of Electrical Engineers)
권호 표지

모듈화된 신경회로망을 이용한 거버 문자 인식 시스템 구현

A Character Recognition System for Gerber File through Modularized Neural Network

  • 오혜원 (충북대학교 대학원 제어계측공학과) ;
  • 박태형 (충북대학교 전기전자컴퓨터공학부)
  • Oh, Hye-Won (Dept. of Control & Instrumentation Eng., Chungbuk National University) ;
  • Park, Tae-Hyong (School of Electrical & Computer Eng., Chungbuk National University)
  • 발행 : 2003.07.21
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

We propose character recognition system for Gerber files. The Gerber file is the vector-formatted drawing file for PCB manufacturing. To consider the special vector format and rotated characters, we develop segmentation and feature extraction method. The modularized neural network is then applied to the recognition algorithm. Finally, comparative simulation results are presented to verify the usefulness of the proposed method.

키워드