• 제어로봇시스템학회논문지
• /
• 제4권4호
• /
• pp.499-505
• /
• 1998

In developing an automated surface inspect algorithm, we have designed a hierarchical classifier using neural network. The defects which exist on the surface of cold mill strip have a scattering or singular distribution. We have considered three major problems, that is preprocessing, feature extraction and defect classification. In preprocessing, Top-hit transform, adaptive thresholding, thinning and noise rejection are used Especially, Top-hit transform using local minimax operation diminishes the effect of bad lighting. In feature extraction, geometric, moment, co-occurrence matrix, and histogram ratio features are calculated. The histogram ratio feature is taken from the gray-level image. For defect classification, we suggest a hierarchical structure of which nodes are multilayer neural network classifiers. The proposed algorithm reduced error rate by comparing to one-stage structure.

• 제어로봇시스템학회논문지
• /
• 제3권2호
• /
• pp.179-186
• /
• 1997

In this paper we suggest a development of surface defect inspection algorithms for cold mill strip. The defects which exist in a surface of cold mill strip have a scattering or singular distribution. This paper consists of preprocessing, feature extraction and defect classification. By preprocessing, the binarized defect image is achieved. In this procedure, Top-hit transform, adaptive thresholding, thinning and noise rejection are used. Especially, Top-hit transform using local min/max operation diminishes the effect of bad lighting. In feature extraction, geometric, moment and co-occurrence matrix features are calculated. For the defect classification, multilayer neural network is used. The proposed algorithm showed 15% error rate.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.365-370
• /
• 1997

In this paper we suggest a development of surface defect inspection algorithms for cold mill strip using tree structure. The defects which exist in a surface of cold mill strip have a scattering or singular distribution. This paper consists of preprocessing, feature extraction and defect classification. By preprocessing, the binarized defect image is achieved. In this procedure, Top-hit transform, adaptive thresholding, thinning and noise rejection are used. Especially, Top-hit transform using local min/max operation diminishes the effect of bad lighting. In feature extraction, geometric, moment, co-occurrence matrix, histogram-ratio features are calculated. The histogram-ratio feature is taken from the gray-level image. For the defect classification, we suggest a tree structure of which nodes are multilayer neural network clasifiers. The proposed algorithm reduced error rate comparing to one stage structure.

• 한국지반공학회논문집
• /
• 제37권11호
• /
• pp.51-60
• /
• 2021

하천의 세굴은 교각 주변의 흙을 침식시켜 교각의 횡방향 지지력을 저감시키고 구조물의 건전도를 저하시키게 된다. 본 연구에서는 세굴이 구조물의 건전도에 미치는 영향을 살펴보고자 주변지반의 굴착에 따른 교각의 고유진동수 측정실험을 수행하였다. 폐교예정인 만경강교의 우물통기초 교각에서 충격진동시험을 수행하였다. 교각의 상단, 중앙, 하단에 가속도계를 부착하고 세 지점을 타격하여 가속도를 계측하였다. 실험 결과, 타격위치에 따른 가속도 측정값 중 상단타격이 일관되고 합리적인 가속도 결과를 보여주었다. 계측된 가속도는 고속 푸리에 변환(FFT)을 통하여 주파수 영역으로 변환되었고, 이를 이용하여 고유진동수를 측정하였다. 또한, 세굴이 교각의 고유진동수 변화에 미치는 영향을 분석하기 위하여 교각 주변 지반을 굴착하면서 고유진동수의 변화를 측정하였다. 그 결과, 굴착 깊이에 따라 고유 진동수가 감소하는 경향을 보여주었지만, 우물통 기초형식이 큰 강성을 가지고 있어 그 감소폭은 작은 것으로 나타났다.