조명의 변화가 심한 환경에서 자동차 부품 유무 비전검사 방법

다국어 초록 (Multilingual Abstract)

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[1]. 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-learning concept for the misclassified data. The effectiveness of the proposed visual inspection method is verified through sufficient experiments in a real sunroof production line.

목차 (Table of Contents)

• Abstract
• I. 서론
• II. 기존 자동차 부품 유-무 비전검사 방법[1]에 대한 문제점 분석
• III. 개선된 자동차 부품 유무 머신비전 검사 방법
• IV. 실험결과
• V. 결론
• REFERENCES

참고문헌 (Reference)

1 이상준, "영상처리와 SVM을 이용한 Billet의 스크래치 결함 분류" 제어·로봇·시스템학회 19 (19): 256-261, 2013

2 S. Lee, "Volts inspection of panorama sunroof frame using polar coordinated histo-gram" 106 : 2013

3 V. Vapnik, "The Nature of Statistical Learning Theory" Springer-Verlag 1995

4 N. Bhatia, "Survey of nearest neighbor techniques" 8 (8): 2010

5 C. Cortes, "Support-vector networks" 20 : 1995

6 김기석, "SVM 학습 알고리즘을 이용한 자동차 썬루프의 부품 유무 비전검사 시스템" 제어·로봇·시스템학회 19 (19): 1099-1104, 2013

7 N. Dalal, "Histogram of oriented gradients for human detection" 1 : 886-893, 2005

8 X. Liang, "Effective method of pruning support vector machine classifiers" 21 (21): 26-38, 2009

9 Y. Freund, "A Short Introduction to Boosting" 14 (14): 771-780, 1999