• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.6
• /
• pp.3416-3422
• /
• 2014

A shock absorber rod is located in the center of the absorber piston and is responsible for the reciprocating movement portion. If it has surface defects, the damping performance of product will be adversely affected. A rod surface has gloss by heat treatment. Therefore, it is difficult to find a defect, such as dust, imprints, and blowholes. Because a total inspection is achieved by visual inspection by workers, it causes eyestrain and the quality of the product is not constant. In this paper, a machine vision system was developed to find a defect using a line-scan camera. The machine can detect surface defects than 0.3mm. To minimize the occurrence probability of defects on the inspection process, the developed auto inspection system had an automatic feeding system and incorporated a protection system. Through the development of this system, which relies on the operator's visual inspection of the surface of the shock absorber, the Rod inspection system constructed quality inspection standards and standardized tests to ensure improved reliability.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.04a
• /
• pp.146-148
• /
• 2002

An automatic inspection vision systems whose development was the industry applications motor rear side member. This system are connected to the 9 ea camera fur the process inspection the bolt, nuts, units in the rear side member product. This automatic inspection vision systems can perform inspection of not attached the bolt, nuts, units, etc fast and accuracy in react time fashion. And then perform very sophisticated inspection which human workers can not perform.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.12
• /
• pp.1109-1114
• /
• 2015

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.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.34 no.2
• /
• pp.121-125
• /
• 2021

The machine vision technology has been widely used in the industrialized nations like the United States, Japan, and EU in the various industries from the late 1980s. Machine vision inspection system mainly consists of a camera, optics, illumination and an image acquisition system. Optimization of the illumination light source is very important. This paper shows a comparison between Pulse Width Modulation (PWM) control and strobe control in driving LED lighting system for machine vision. PWM control method has problems such as a temperature rising of LED and a flickering in image measurement for inspection. In contrast, the proposed strobe control method can suppress the temperature of LED light source below 40℃. Also, it can remove the flickering problem through a synchronization between a frame grabber and a camera shutter. Finally, the strobe control method was shown to extract clearer images with a high precision compared to PWM control method.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.409-415
• /
• 2022

In computer vision, an image of a measurement target is acquired using a camera. And feature values, vectors, and regions are detected by applying algorithms and library functions. The detected data is calculated and analyzed in various forms depending on the purpose of use. Computer vision is being used in various places, especially in the field of automatically recognizing automobile parts or measuring the quality. Computer vision is being used as the term machine vision in the industrial field, and it is connected with artificial intelligence to judge product quality or predict results. In this study, a vision system for judging the quality of automobile parts was built, and the results were compared by applying five machine learning classification models to the produced data.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.6
• /
• pp.14-20
• /
• 2009

The goal of image processing is to improve the visual appearance of images for human viewers. The histogram is an important tool which can be used as basic data of digital image processing. Therefore, to effectively manage a histogram in digital image processing is very important. Currently machine vision systems are used in many appearance inspection fields instead of inspection by human. However, the appearance inspection result by machine vision system is mainly influenced by illumination of workplace. In this paper, we propose a histogram transform method for improving accuracy of machine visual inspection. The enhancement effect of area feature is obtained by performing proposed histogram transformation in area that needs improvement The proposed algorithm is verified by appearance inspection of jig plate samples.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.4
• /
• pp.16-29
• /
• 1993

The objective of this research is in the development of a flexible 3-dimensional inspection system for the sculptured surface by integrating the Coordinate Measuring Machine (CMM), CAD database, and vision system. To achieve the proposed flexible inspection system, two research categories are discussed in the study: new inspection planning method includes a new measuring point selection method and various new probe path generation methods. The object recognition and localization process for the unknown surface can be easily carried out by introducing a new concept called "Z-Layer". The experimental results indicate that the developed flexible inspection system, with the proposed algorithm, can be inplemented in real situation.situation.

• Journal of Korean Society for Quality Management
• /
• v.32 no.1
• /
• pp.63-74
• /
• 2004

Recently, enterprises have focused on quality improvement for delighting their customers. Especially, all business sector have checked, analyzed their consumer complaints in detail on their products and made a plan to reduce them. But there is a limitation not to solve them. This paper presents one of tools to reduce non qualified product on their operation line directly by modernized IT technology after analyzing and making the plan.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.11a
• /
• pp.517-518
• /
• 2008

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.12
• /
• pp.1072-1080
• /
• 2013

In a the present day, many vision inspection techniques are used in productive industrial areas. In particular, in the semiconductor industry the vision inspection system for wafers is a very important system. Also, inspection techniques for semiconductor wafer production are required to ensure high precision and fast inspection. In order to achieve these objectives, parallel processing of the inspection algorithm is essentially needed. In this paper, we propose the GPU (Graphical Processing Unit)-based parallel processing algorithm for the fast inspection of semiconductor wafers. The proposed algorithm is implemented on GPU boards made by NVIDIA Company. The defect detection performance of the proposed algorithm implemented on the GPU is the same as if by a single CPU, but the execution time of the proposed method is about 210 times faster than the one with a single CPU.