• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.3
• /
• pp.42-50
• /
• 2008

We developed a visual inspection system for detecting defective products. Most existing inspection systems are designed to be dedicated to one product, which makes operator spend extra money and time to adopt other products. In this work, we propose a flexible visual inspection system that can inspect various products without any additional major job at a low-cost. The developed system contained image processing algorithm libraries and user-friendly graphic interface for adaptable image-based inspection system. We can find a proper threshold value using the proposed algorithm which uses correlation coefficient between a non-defective product and existing sample images of defective product. And We tested the performance of the proposed algorithm using Otsu's method. The proposed system is applied to a automated inspection line for cellular phone.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.2
• /
• pp.335-341
• /
• 2017

This paper proposes an image-processing algorithm for inspecting double-cut defects in the motor shaft manufacturing process. The algorithm consists of extracting the outline using the brightness of the image, obtaining a binarized boundary graph using the extracted outline, and determining the defects from the graph. Defects in which two cut surfaces are separated are considered type 1 defects, and those in which two cut surfaces are connected are defined as type 2 defects. In an actual manufacturing process, 112 good samples and 44 defective samples (34 type 1 defects and 10 type 2 defects) were collected and used to verify the algorithm. The samples were judged with 100% accuracy for both type 1 and type 2 defects. The algorithm will be used in the field after securing reliability for various samples.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.103-106
• /
• 2013

3D LCD Module은 기존 TFT-LCD에 Parallax Barrier 방식과 Passive Glasses 방식 및 Active Glass 방식의 기술을 적합하여 만들어 진다. 현재는 3D Module 제작 후 기타 ASSY 장치를 부착 하여 시제품 출시 전에 3D 패턴을 기반으로 출하 검사를 통해 제품 이상 유무를 검사하다 보니 제품 출하 검사 시 불량 요인으로 불량 제품에 대한 모든 Repair공정을 위해 많은 시간 및 인력, 자재 등의 많은 로스 부분이 발생 하여 생산성 절감 및 제품 원가 상승의 요인이 발생 한다. 따라서 본 논문에서 제안하고자 하는 내용은 기존의 2D TFT-LCD Module 검사장비에 3D Pattern 및 동영상을 구현하여 보다 신속 하고 정확한 임베디드 환경을 이용한 2D 및 3D LCD Module용 검사 시스템을 개발 하는데 있다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.87-93
• /
• 2012

In this paper, we proposed a faulty pattern detection algorithm of TCP(Tape Carrier Package)/COF(Chip On Film), and implemented a real-time system for inspecting TCP/COF. Since TCP/COF has very high resolution having several micro meters, the human operator should visually inspect all the parts through microscope. In this work, we implement an inspection system to detect the faulty pattern, so the operator can visually inspect only the designated parts by the inspection system through the monitor. The proposed defects detection algorithm for TCP/COF packages is implemented by the pattern matching method based on subtracting the reference image from test image. To evaluate performance of the proposal system. we made various experiments according to type of CCD camera and light source as well as illumination projection method. From experimental results, it is confirmed that the proposed system makes it possible to detect effectively the defective TCP/COF film.

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.6
• /
• pp.11-16
• /
• 2021

In this paper, a quality inspection system was developed to identify the defective assembly of connectors used in automobile wiring. For waterproof connectors, an internal seal must be inserted for waterproofing. However, there are cases where it is omitted or double-inserted during production. An automatic inspection jig was designed using photosensors and touch switches to classify good and bad connector components. In the case of the existing visual inspection, 6,400 connectors were inspected when 5 people inspected for 8 hours. However, when using the inspection jig developed under the same conditions, 20,000 pieces were inspected. In other words, the productivity is greatly improved compared to the conventional visual inspection.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.7
• /
• pp.1737-1742
• /
• 2015

In the industrial field for product inspection needs not only on the surface of the product but also the internal components defect inspection. Generally, optical inspection is mainly used for item inspection from production process. However, this is only to check defect of surface it is difficult to perform inspection of goods internal. To overcome these limitations, Instead of optical device by using the portable X- ray DR image acquisition device system developed to obtain an image in real time at the same time and determine product defects. After obtaining the X- ray image, the inspection product within error range is passed after machine image processing. Also, the results and numbers are stored by users.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.5
• /
• pp.1558-1563
• /
• 2010

This paper describes a study on algorithm for the development of machine vision system as well as the inspection of automobile's plastic part locking lever to replace a human worker's eye inspection. Before developing the machine vision system based on the PC, the purpose of this research is to develop the algorithm to decide whether a product is a good/bad one in real time inspection. NI-LabVIEW software is used in the inspection method and an inspection program is developed using LabVIEW Vision image functions. The inspection program was built and validated to help the system operator set up the inspection area and change the criteria number in the program.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.10a
• /
• pp.193-198
• /
• 2001

생산현장 업무에서는 측정검사업무의 비중이 크다. 측정검사의 업무는 품질향상을 위한 활동이며 또한 고부가가치의 제품을 위해서도 중요하다. 고품질 고정밀도는 철저한 측정검사를 통하여 이루어진다. 제품의 치수를 정확히 측정하여 정밀도 있는 부품을 제작하고 불량부품이나 파손된 부품을 검사하여 제거함으로써 제품의 성은과 품질이 우수하게 인정된다. 이러한 측정검사작업의 정밀도향상, 생산성 향상을 위해서는 자동화가 필요하다. 측정검사의 자동화 (CAT : Computer Aided Testing)에는 영상처리를 이용하는 시각검사의 자동화가 중요한 분야이다. 영상처리를 이용한 시각검사의 대상은 결함검사, 두께검사, 형상칫수 검사, 물체의 위치, 방향, 종류의 파악 등이 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.289-290
• /
• 2024

PCB(Printed circuit board)생산시에 중요한 역할을 담당하는 비전검사 시스템의 성능은 지속적으로 발전해왔다. 기존 머신 비전 검사 시스템은 이미지가 불규칙하고 비정형일 경우 해석이 어렵고 전문가의 경험에 의존한다. 그리고 비전검사 시스템 개발 당시의 기준과 다른 불량이 발생한다면 검출이 불가능 하거나 정확도가 낮게 나온다. 본 논문에서는 이를 개선하고자 딥러닝 영상인식을 이용한 PCB 기판 비전 검사 시스템을 구현하였다. 딥러닝 영상인식 알고리즘은 YOLOv4를 이용하고, 워핑(warping)과 시킨 PCB 이미지를 학습하여 비전검사 시스템을 구성하였다. 딥러닝 영상인식 기술의 처리 속도를 보완하고자 QR코드로 PCB 기판 종류를 인식하고, 해당 PCB 부품의 미삽은 정답 이미지 바운딩 박스 좌표와 비교하여 불량품을 발견하면 표시해준다. 기판의 부품 인식을 위해 기판 데이터는 직접 촬영하여 수집하였다. 이를 활용하여 PCB 생산 공정에서 비전검사 시스템의 성능이 향상되었고,, 다양한 PCB를 생산에 신속하게 대응할 수 있다.

• The monthly packaging world
• /
• s.114
• /
• pp.148-153
• /
• 2002