• Journal of the Optical Society of Korea
• /
• v.11 no.4
• /
• pp.173-176
• /
• 2007

We present a very simple and efficient bare-wafer inspection method using a knife-edge test. The wafer front surface and inner structures are inspected simultaneously. The wafer front surface is inspected visually using a knife-edge test while the inner structure is simultaneously inspected by a camera in the infrared region with a single white-light source. This paper presents a laboratory implementation of the test method with some experimental results.

• Proceedings of the Optical Society of Korea Conference
• /
• 2007.07a
• /
• pp.65-66
• /
• 2007

We present a new simple and fast bare-wafer inspection method. This method inspects the wafer front surface and inner structures simultaneously. The wafer surface is inspected using a knife-edge test in visible while the inner structure is inspected by a looking-through camera in infrared, at the same time and with a single white-light source. This paper presents a laboratory implementation of the test method with some experimental results.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.3056-3059
• /
• 2000

This paper describes a fast image labeling algorithm for the feature extraction of connected components. Labeling the connected regions of a digitized image is a fundamental computation in image analysis and machine vision, with a large number of application that can be found in various literature. This algorithm is designed for the surface defect inspection of Cold Mill Strip. The labeling algorithm permits to separate all of the connected components appearing on the Cold Mill Strip.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.5 no.4
• /
• pp.155-160
• /
• 2001

KS-code(KS B 0896) for nondestructive ultrasonic testing classifies the quality level by relative flaw size only. But flaw position is more important than the flaw size. Test blocks having artificial holes near surface show lower yield load than the blocks having deeply located holes from the surface. So, level calibration table was proposed for classifying the quality level of welded steel structures.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.5
• /
• pp.870-876
• /
• 2017

In this paper, we proposed the automatic vision inspection system using multi-layer perceptron to detect the defects occurred on rail surface. The proposed system consists of image acquisition part and analysis part. Rail surface image is acquired as equal interval using line scan camera and lighting. Mean filter and dynamic threshold is used to reduce noise and segment defect area. Various features to characterize the defects are extracted. And they are used to train and distinguish defects by MLP-classifier. The system is installed on HEMU-430X and applied to analyze the rail surface images acquired from Honam-line at high speed up to 300 km/h. Recognition rate is calculated through comparison with manual inspection results.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.7 no.2
• /
• pp.141-148
• /
• 2003

Concrete surface is a part that resists chiefly to carbonation by carbonic acid gas, affluence of rainwater and air, deterioration by freezing thawing, salt damage by seawater, and other chemical erosion etc. Therefore, this research analyzed physical characteristic and durable characteristic of concrete eliminated glut water and bubble of concrete surface using CON-SILK that is permeated with dehydration. As a research result, concrete using CON-SILK was improved, in comparison with concrete using general formwork, in physical performance and durability of concrete, as surface hardness, carbonation resistivity, and salt content permeation resistivity etc. Therefore, we could know that it is effective to use CON-SILK in performance elevation of concrete surface.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.12
• /
• pp.60-70
• /
• 1999

An efficient automatic inspection system for Floating Seal is developed, The proposed system consists of a high resolution line scan camera, microcomputer, and PLC (Programmable Logic Controller). In order to perform rapid inspection, The ROI (Region of Interest) is extracted from the original image. There are types of defects; shape defects and surface defects. Each features of defects are captured by edge detect, segmentation, morphological operation, and threshold analysis. PLC controller is used to synchronize the whole system and store the inspection results temporarily to reduce the overhead of microcomputer. As a result, the system is being utilized successfully in a teal inspection line.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.952-956
• /
• 1995

It is known that the 3D Solid CAD system can provide various information which is useful for implementing CAPP and CAE. However the commercial 3D CAD systems available today do not support the handling of non-geometric information such as geometry tolerance and surface finish. It is impossible to input the non-geometric information during designof parts while CAPP needs the information for selecting machine tools. fiztures, inspection method, etc. In this paper the need of research on handling tolerance information In 3D CAD systems is considered. The development of inspection planning support system is also explained with an example. The development of inspection planning support systm receives the design geometry information from the 3D CAD system in the form of 2D draft and generates the inspection data base and the inspection sheet through the user interaction.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2453-2455
• /
• 2003

We propose a path planning method to reduce the inspection time of AOI (automatic optical inspection) machines in SMT (surface mount technology) in-line system. Inspection windows of board should be clustered to consider the FOV (field-of-view) of camera. The number of clusters is desirable to be minimized in order to reduce the overall inspection time. We newly propose a genetic algorithm to minimize the number of clusters for a given board. Comparative simulation results are presented to verify the usefulness of proposed algorithm.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.505-510
• /
• 2024

Since rolling contact fatigue cracks can always occur on the rail surface, which is the contact surface between wheels and rails, railway rails require thorough inspection and diagnosis to thoroughly inspect the condition of the cracks and prevent breakage. Recent detailed guidelines on the performance evaluation of track facilities present the requirements for methods and procedures for track performance evaluation. However, diagnosing and grading rail surface damage mainly relies on external inspection (visual inspection), which inevitably relies on qualitative evaluation based on the subjective judgment of the inspector. Therefore, in this study, we conducted a deep learning model study for rail surface defect detection using Fast R-CNN. After building a dataset of rail surface defect images, the model was tested. The performance evaluation results of the deep learning model showed that mAP was 94.9%. Because Fast R-CNN has a high crack detection effect, it is believed that using this model can efficiently identify rail surface defects.