• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.389-390
• /
• 2006

The goal of this paper is automation of a remocon inspection process using machine vision system. This system prevents error that is occurred by physical and spirit condition of human. Also this system has been developed to raise the reliability of remocon inspection. This system has been developed only using PC, CCD Camera and Visual C++ for universal workplaces. The performance of this system is an accuracy improvement of $2{\sim}3[%]$ and a processing time reduction of about 100[ms] against existing pattern matching method.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1940-1944
• /
• 2004

• 산업공학
• /
• 제10권3호
• /
• pp.133-143
• /
• 1997

In this paper, an improved method is developed for automatic inspection system using simbology patterns. The developed method uses the two previously developed matching methods the template maching method and the feature matching method. The template matching method is very sensitive to variations of target images such as translation and rotation of objects. On the other hand, the feature matching method doesn't extract proper features in some types of symbology patterns. The proposed method shows the improvement of precision in recognition of defects and flexibility of different types of symbology patterns.

• 한국도로학회논문집
• /
• 제19권2호
• /
• pp.103-112
• /
• 2017

PURPOSES : In this study, field performance evaluation of crack treatment of pavement and the feasibility of surface treatment of pavement are presented. The performance and cost of preventive maintenance methods have been previously verified, and the methods are being used in many developed countries and cities. However, the performance and cost of the system have not been verified in domestic, field applications. Therefore, in order to improve performance, the field performance is evaluated, and a reasonable cost is proposed. METHODS : Visual Inspection was conducted to evaluate the field application and performance of the preventive maintenance method. In addition, the PCI index was calculated from the results of visual inspection of the application area of the surface treatment method, and the performance life of each method was predicted. For the economic evaluation, life cycle cost analysis was performed using the life cycle cost analysis program. RESULTS :In order to evaluate and quantify the field performance of crack repair material, the residue condition of the pavement surface after crack treatment, rather than the performance of the material, is evaluated. In addition, the crack resistance and performance life of surface treatment methods are evaluated. The cost of currently available treatment methods are compared to the common pavement cut and overlay method, and it is determined that the preventive method is not economical based on life cycle cost analysis. CONCLUSIONS :Because of the characteristics of cracking, it is necessary to conduct the evaluation of currently applied methods and the analysis of the cause of damage, by visual inspection. Moreover, in order to evaluate the performance and economic suitability of the currently applied surface treatment methods, it is necessary to acquire information on application sections by monitoring their long-term conditions and performance.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권3호
• /
• pp.211-216
• /
• 2011

The detection of defective parts in a factory is usually performed by the human eye. Therefore, heavy manpower is in demand for minor enterprises. An image processing system is desired to solve this drawback. However, due to the variety of the products characteristics, an general algorithm is needed that can adapt to these characteristics. Therefore, in this paper, the key pad parts' characteristics which need to be dealt with are analyzed in order to embody the image processing algorithm that is suggested. The experimental results show the probability of detecting a defective part is 95% with a detection time of 0.203 seconds, on the average.

• 산업공학
• /
• 제11권3호
• /
• pp.15-22
• /
• 1998

A new improved algorithm in edge location to subpixel accuracy using decent-based weight to spatial information is proposed in this paper and applied to automated visual inspection(AVI) system. An application of the new edge operator as an edge detector is also provided and compared with Tabatabai and Lyvers edge detectors. The existing algorithms located edger to subpixel accuracy using least-square or moment-based methods. The algorithms also use only spatial information or grey-level values to locate edges. However, the proposed algorithm consider the weighted sum of grey-levels values of each edge pattern. The results show that the proposed algorithm is relatively less biased and has smaller standard deviation than the edge operations developed by Tabatabai and Lyvers in the presence of noise.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1998년도 춘계학술대회 논문집
• /
• pp.310-315
• /
• 1998

This study includes noise automatic inspection system for washing machine auto-transmission one of modern home necessary. We effort to find and certificate sound noisesource by sound power and sound intensity, and apply to frequency analysis in vibration related sound noise. Still more we have been studying to data acquisition and programming for MS VisualBasic version 5.0. System component is below. 1) Pentium PC for data acquisition. 2) DSO for noise acquisition. 3) S/W for comparison and decision. 4) I/F Board for data communication. Wave form data through the DSO are converting to ASCII code data. The ASCII code through binary converting S/W are to be decision fitness or the badness comparison S/W. Finally, we will making noise monitoring system and automatic inspection system.

• 전자공학회논문지SC
• /
• 제49권1호
• /
• pp.8-11
• /
• 2012

자동 결함 검사 시스템 (AVI - Automated Vision Inspection Systems)은 디지털 영상을 통하여 표면의 결함을 자동으로 검출해 주는 시스템이다. 일반적으로 AVI 시스템의 성능은 한도 결함 검출력으로 판별한다. 한도 결함이란 결함 신호가 배경신호와 매우 유사하여 명확히 결함을 검출하기 어렵다. 본 논문에서는 신호대잡음비 (SNR - Signal to Noise Ratio)를 개선할 수 있는 전처리 기법을 제안하였다. 제안된 기법은 인간 시각 시스템 (HVS - Hunman Visual System) 원리를 기반으로 하였으며 이를 RLC (Run Length Code)로 구현하였다. 실험결과 제안된 전처리 기법은 한도 결함 영상에 대해 SNR이 두 배 이상 개선되는 효과를 보였으며 이를 이용하면 AVI 시스템의 검출성능 향상을 기대할 수 있다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2006년도 춘계학술대회 논문집
• /
• pp.327-328
• /
• 2006

Recently, as the infocomindustry is developed, the semiconductor industry as well as the optical industry such as the optical communication and the optical instrument is developed rapidly. The transmission, storage and processing of information has been reaching an limit because amounts of information increase rapidly. The more quickly the optical communication is developed, the more sharply the demand of optical elements increase. The transport and inspection process is time consuming and the error rate is high, because this process are not automated in case of an optical lens. In this paper, the pick-up system that can hold optical elements and be transferred by the ultrasonic transport system is developed. The inspection system that distinguishes between the existence and the nonexistence of a defect is connected easily to pick-up system. The pick-up system separates the optical glass lens by results of the inspection. The automation program is developed by visual c++ programming.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2009년도 춘계학술대회 논문집
• /
• pp.483-484
• /
• 2009