• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.3
• /
• pp.372-377
• /
• 1998

This paper deals with the detection, feature extraction and classification of surface defects in cold rolled strips. Inspection systems are one of the most important fields in factory automation. Defects such as slipmark and dullmark can be effectively detected with a Gaussian matched filter because their shapes are similar to Gaussian. It is justified that the proposed WF(Wavelet Frame) method could be regarded as multiscale Gaussian matched filter which can be applied to the inspection of cold rolled strip. After a wavelet frame transform, the entropies and moments are computed for each subband which pass through both local low pass filter and nonlinear operator. With these features as input, a MLP(Multi Layer Perceptron) is used as a classifier. The proposed inspection method was applied to the real images with defects, and hence showed good performance. The role of each extracted feature is analyzed by KLT(Karhunen-Loeve Transform).

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.7
• /
• pp.619-625
• /
• 2015

There is a large interest to find reliable and automatic methods for crack detection and quantification in the railway bogie frame. The non-destructive inspection of railway bogie frame has been performed by ultrasonic and magnetic particle testing in general inspection. The magnetic particle method has been utilized in the defect inspection of the bogie frame but the grinding process is required before inspection and the dust is developed resulting from the processing. The objective of this paper is to apply the inspection method of bogie frame using infra-red thermography. The infra-red thermography system using the excitation of eddy current was performed for the defect evaluation of weld specimen inserted artificial defects. The result shows that the infra-red thermography method can detect the surface and inner defects in weld specimen for bogie frame.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.574-576
• /
• 2010

In this paper, we propose a development of high speed inspection system which allows the inspection of width, definition and flaws in lead-frame using CCD camera. This system consists of the parts of lighting, inspection, lighting control, GUI and more and developed techniques used are lighting control, fast inspection algorithm and advanced measurement technique for improvement in resolution. The effectiveness in proposed method is proved by conducting field tests.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.4
• /
• pp.1559-1564
• /
• 2011

This study presents the development of a machine vision inspection system(MVIS) purposely for car seat frames as an alternative for human inspection. The proposed MVIS is designed to meet the demands, features and specifications of car seat frame manufacturing companies in striving for increased throughput of better quality. This computer-based MVIS is designed to perform quality measures by detecting holes, nuts and welding spots on every car seat frame in real time. In this study, the NI Vision Builder software for Automatic Inspection was used as a solution in configuring the aimed quality measurements. The techniques for visual inspection are optimized through qualitative analysis and simulation of human tolerance on inspecting car seat frames. Furthermore, this study exemplifies the incorporation of the optimized vision inspection environment to the pre-inspection and post-inspection subsystems. The system built on this proposed MVIS for car seat frames has successfully found the possible detections.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.5
• /
• pp.359-363
• /
• 2017

The LED (Liquid Emitting Diode) frame device is a big part of the representative display industry in Korea. LED is an essential part for TV, monitor, notebook, and mobile phone. In Japan, Taiwan, China and other countries, investment in LEDs has been strengthened, and productivity has become an important issue. However, as the size of the parts becomes smaller, the inconsistent inspection by the human eye becomes a problem of reliability, so that the automatic inspection process becomes an essential issue in the field of LED module inspection. In this paper, we investigate defects in visual inspection process using computer vision technology. The inspection of the LED frame is made quickly and accurately, thereby improving the efficiency of the process and shortening the inspection time. As a result of applying the inspection system to the field, we confirmed that it is possible to inspect quickly and accurately.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.10a
• /
• pp.827-829
• /
• 2014

This paper presents a design methodology for improving dynamic stiffness of an inspection robot frame to prevent resonance. Finite element models of robot frame are developed for natural frequency analysis. Natural frequency analysis of robot frame is conducted to compare with sub-span oscillation which is excitation frequency. Reinforcement beams are applied to the sensitive parts of the robot frame to improve dynamic stiffness using case study. To reduce mass of the robot frame, thickness optimization of the robot frame is carried out by utilizing response surface method. The result of optimization show that dynamic stiffness of robot frame is increased. As a result, natural frequency of an optimal model is not included in range of frequencies of the sub-span oscillation.

• Journal of Auto-vehicle Safety Association
• /
• v.9 no.4
• /
• pp.55-60
• /
• 2017

This paper presents the motorcycle inspection standards of electrical system, frame & body, lights and speedometers. 187 real-world motorcycles are visually and mechanically inspected according to the developed inspection standards. The non-compliance rate of inspection standards of the lights is 23.7% and main causes are damage, tinting, painting and coloration of head-lamp, number plate lamp, front-rear position lights, stop lamp and direction indicators of motorcycles. Also, 28.4% of motorcycles are dropped from the luminous intensity inspection standard. Motorcycle electrical system cannot be visually inspected. The motorcycle inspections standards are improved reflecting 187 cases of real-world motorcycle inspection results.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.492-498
• /
• 1994

The bicycle production process mainly consists of welding process of pipes and its quality is determined by geometrical symmetry of arrangement of welded pipes. Hence, manual quality control of bicycle frames was very inefficient and required much time in dimentional inspection and does not reserve high precision. In this paper we introduce a method of fast and accurate dimensional inspection of bicycle frame using the Stereo Vision system and related some image processing techniques.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.5
• /
• pp.740-745
• /
• 2008

This paper presents a new non-contact 3D robotic inspection system to measure the precise positions of screw and punch holes on a car body frame. The newly developed sensor consists of a CCD camera, two laser line generators and LED light. This lightweight sensor can be mounted on an industrial robot hand. An inspection algorithm and system that work with this sensor is presented. In performance evaluation tests, the measurement accuracy of this inspection system was about 200 ${\mu}m$, which is a sufficient accuracy in the automotive industry.

• 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.