• Corrosion Science and Technology
• /
• 제18권6호
• /
• pp.253-257
• /
• 2019

A deep learning based real-time painting surface inspection algorithm is proposed herein, designed for developing an autonomous inspection drone. The painting surface inspection is usually conducted manually. However, the manual inspection has a limitation in obtaining accurate data for correct judgement on the surface because of human error and deviation of individual inspection experiences. The best method to replace manual surface inspection is the vision-based inspection method with a camera, using various image processing algorithms. Nevertheless, the visual inspection is difficult to apply to surface inspection due to diverse appearances of material, hue, and lightning effects. To overcome technical limitations, a deep learning-based pattern recognition algorithm is proposed, which is specialized for painting surface inspections. The proposed algorithm functions in real time on the embedded board mounted on an autonomous inspection drone. The inspection results data are stored in the database and used for training the deep learning algorithm to improve performance. The various experiments for pre-inspection of painting processes are performed to verify real-time performance of the proposed deep learning algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.171-171
• /
• 2000

We have developed m innovative surface inspection system for automated quality control for steel products in POSCO. We had ever installed the various kinds of surface inspection systems, such as a linear CCD and a laser typed surface inspection systems at cold rolled strips production lines. But, these systems cannot fulfill the sufficient detection and classification rate, and real time processing performance. In order to increase detection and classification rate, we have used the Dark, Bright and Transition Field illumination and area type CCD camera, and fur the real time image processing, parallel computing has been used. In this paper, we introduced the automatic surface inspection system and real time image processing technique using the Object Detection, Defect Detection, Classification algorithms and its performance obtained at the production line.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 추계학술대회 논문집
• /
• pp.444-449
• /
• 1996

The semiconductor, which is precision product, requires many inspection processes. The surface conditions of the semiconductor chip affect on the functions of the semiconductors. The defects of the chip surface are cracks or voids. As general inspection method requires many inspection procedure, the inspection system which searches immediately and precisely the defects of the semiconductor chip surface is required. We suggest the detection algorithm for inspecting the surface defects of the semiconductor surface. The proposed algorithm first regards the semiconductor surface as random texture and point spread function, and secondly presents the character of texture by linear estimation theorem. This paper assumes that the gray level of each pixel of an image is estimated from a weighted sum of gray levels of its neighbor pixels by linear estimation theorem. The weight coefficients are determined so that the mean square error is minimized. The obtained estimation window(two-dimensional estimation window) characterizes the surface texture of semiconductor and is used to discriminate the defects of semiconductor surface.

• 반도체디스플레이기술학회지
• /
• 제18권3호
• /
• pp.60-65
• /
• 2019

In this paper, the hybrid illumination system for effectively detecting surface defects in steel plate with lowcontrast, non-uniformity and featureless is designed based on illuminance uniformity. First of all, characteristics of steel plate defects were considered and typical inspection illumination system is implemented. Optimum illumination parameters for uniformly illuminating an inspection area in the typical illumination system are selected based on the illuminance uniformity and illuminance distribution measurement. The illuminance uniformity and illuminance distribution are measured using an illuminometer based on the arduino. Through illuminance distribution analysis of the typical illumination, an hybrid illumination is designed by fusing bi-directional illumination and coaxial illumination. The hybrid illumination showed higher uniformity ratio and illuminance distribution than the typical illuminations. The hybrid illumination system showed the ability to uniformly illuminate the entire inspection region of steel plate surface.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1996년도 춘계학술대회 논문집
• /
• pp.24-29
• /
• 1996

The seniconductor, which is precision product, requires many inspection processes. The surface conditions of the semiconductor chip effect on the functions of the semiconductors. The defects of the chip surface is crack or void. Because general inspection method requires many inspection processes, the inspection system which searches immediately and preciselythe defects of the semiconductor chip surface. We propose the inspection method by using the computer vision system. This study presents an image processing algorithm for inspecting the surface defects(crack, void)of the semiconductor test samples. The proposed image processing algorithm aims to reduce inspection time, and to analyze those experienced operator. This paper regards the chip surface as random texture, and deals with the image modeling of randon texture image for searching the surface defects. For texture modeling, we consider the relation of a pixel and neighborhood pixels as noncasul model and extract the statistical characteristics from the radom texture field by using the 2D AR model(Aut oregressive). This paper regards on image as the output of linear system, and considers the fidelity or intelligibility criteria for measuring the quality of an image or the performance of the processing techinque. This study utilizes the variance of prediction error which is computed by substituting the gary level of pixel of another texture field into the two dimensional AR(autoregressive model)model fitted to the texture field, estimate the parameter us-ing the PAA(parameter adaptation algorithm) and design the defect detection filter. Later, we next try to study the defect detection search algorithm.

• 한국산학기술학회논문지
• /
• 제15권6호
• /
• pp.3416-3422
• /
• 2014

쇼크 업쇼바의 로드는 피스톤부 중심에 위치하여 왕복운동을 담당하는 부분으로 표면의 불량(찍힘)이 있을 경우 감쇠력에 대한 차이로 제품 성능을 제대로 발휘하는데 문제 발생의 요인이 되고 있다. 로드표면은 열처리 상태로 표면 광택으로 인하여 쉽게 불량이 표시되지 않으며, 작업자가 육안으로 로드의 이물질 및 찍힘, 기포 검사를 진행함으로써 눈의 피로도가 높아지고, 작업자 육안에 의존하기 때문에 제품의 검사 품질이 일정하지 않다. 본 연구에서는 제품의 원통 형상을 고려하여 라인스캔카메라를 이용한 머신비전 영상처리 기법으로 0.3mm이상의 표면의 불량을 검출하고, 검사단계에서 발생할 수 있는 표면 불량을 최소화하기 위한 전 공정 자동이송 및 양불 제품의 혼입을 방지하는 자동검사 시스템 개발에 대한 연구를 수행하였다. 표면검사 시스템 개발로 작업자의 육안 검사에 의존하고 있던 쇼크업쇼버 로드의 표면에 대한 정밀 검사시스템 구축으로 품질검사 기준을 확보하고 표준화된 검사로 신뢰도가 향상되었다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2004년도 추계학술대회 논문집
• /
• pp.323-326
• /
• 2004

In this study, the inspection path which is considered to free collision is generated by offset surface. When the inspection is executed, the consideration of machine dynamic error increases a precision. Dynamic error is measured on CNC machine bed changing of weight work price. Offset surface is safety space about collision. Because the danger of probe-collision is excluded in Offset surface, it is possible to rapid feed of probe and reduced inspection time. The Program which is possible to simulate using CAIP and is confirmed through actual experiment.

• 한국기계가공학회지
• /
• 제20권10호
• /
• pp.112-118
• /
• 2021

In this study, an inspection method using a color image is proposed to conduct a real-time inspection of covalent organic framework (COF) films to detect defects, if any. The COF film consists of an upper pattern SR and a lower PI. The proposed system detects the defects of more than 20 ㎛ on the SR surface owing to the characteristics of the pattern, whereas on the PI surface, it detects defects of more than 4 ㎛ by utilizing a micro-optical system. In the existing system, it is difficult for the operator to conduct a full inspection through a high-performance microscope. The proposed inspection algorithm performs the inspection by separating each color component using the color contrast of the pattern on the SR side, and on the PI surface it inspects the bonding state of the mounted chip. As a result, it is possible to confirm the exact location of the defects through the SR and PI surface inspections in the implemented inspection.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제10권1호
• /
• pp.31-45
• /
• 2006

최근 고집적화, 고밀도화 되어가는 첨단 디바이스와 섬세한 공정들은 SMT(surface mounting technology)에서의 더욱 까다로운 검사 항목들을 요구하고 있다. 특히, 어셈블리 생산품의 불량의 60% 이상을 차지하는 솔더 프린팅의 검사는 이러한 추세에 대응책으로 3차원적인 검사방식이 기존의 2차원적인 검사방식을 빠르게 대치해나가고 있다. 따라서 본 논문에서는 SMT 어셈블리 라인에서 PCB(Printed circuit board)에 프린팅된 솔더 페이스트에 대한 3차원적인 검사를 자동으로 수행하는 인라인형의 고속 3차원 검사 장비 및 측정 알고리즘을 제안한다. 제안한 방법은 3차원 데이터를 B-스플라인으로 표면을 구성한 다음 이를 기반으로 패드를 추출하고, 검사하는 알고리즘이다.

• 한국정밀공학회지
• /
• 제26권7호
• /
• pp.58-64
• /
• 2009

In this paper, an inspection mechanism based on laser scattering has been developed for the surface evaluation of infrared cut-off filters, and optimum conditions of laser scattering are determined using the design of experiment. First of all, attributes and influence factors of laser scattering are investigated and then a laser scattering inspection mechanism is newly designed based on analyses of laser scattering parameters. Also, Taguchi method, one of experimental designs, is used for the optimum condition selection of laser scattering parameters and the optimum condition is determined in order to maximize the detection capability of surface defects. Experiments show that the proposed method is useful in a consistent and effective defect detection and can be applied to surface evaluation processes in manufacturing.