본문 바로 가기

로고

국내 최대 기계 및 로봇 연구정보
통합검색 화살표
  • 시편연마기 Mecatech 334
  • 국내학술지

    235 0
    국내학술지 제목 게시판 내용
    제목(국문) 조명의 변화가 심한 환경에서 자동차 부품 유무 비전검사 방법
    제목(영문) Auto Parts Visual Inspection in Severe Changes in the Lighting Environment
    저자 김기석 (Giseok Kim ,School of Computer Science and Engineering, Korea University of Technology and Education ) ▷공저자네트워크등록하기
    박요한 (Yo Han Park ,School of Computer Science and Engineering, Korea University of Technology and Education ) ▷공저자네트워크등록하기
    박종섭 (Jong-Seop Park ,School of Computer Science and Engineering, Korea University of Technology and Education ) ▷공저자네트워크등록하기
    조재수 (Jae-Soo Cho ,School of Computer Science and Engineering, Korea University of Technology and Education ) ▷공저자네트워크등록하기
    초록
    초록(영문)

    This paper presents an improved learning-based visual inspection method for auto parts inspection in severe lighting changes. Automobile sunroof frames are produced automatically by robots in most production lines. In the sunroof frame manufacturing process, there is a quality problem with some parts such as volts are missed. Instead of manual sampling inspection using some mechanical jig instruments, a learning-based machine vision system was proposed in the previous research[l]. But, in applying the actual sunroof frame production process, the inspection accuracy of the proposed vision system is much lowered because of severe illumination changes. In order to overcome this capricious environment, some selective feature vectors and cascade classifiers are used for each auto parts. And we are able to improve the inspection accuracy through the re-Ieaming concept for the rnisclassified data. The effectiveness of the proposed visual inspection method is verified through sufficient experiments in a real sunroof production line.

    keyword auto parts visual inspection, machine vision, adaboost, kNN, selective feature vector
    저널명 제어로봇시스템학회논문지 ▷관련저널보기
    VOL 21
    PAGE 1109
    발표년도 2015
    국문File 국문다운로드
    영문File
    • 페이스북아이콘
    • 트위터 아이콘

    서브 사이드

    서브 우측상단1