• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.367-370
• /
• 2016

QFN(Quad Flat No-leads package) is one of the SMD(Surface Mount Device). Since there is no lead in QFN, there are many defects on solder. Therefore, we propose an efficient mechanism for QFN solder defect detection at this paper. For this, we employ Convolutional Neural Network(CNN) of the Machine Learning algorithm. QFN solder's color multi-layer images are used to train CNN. Since these images are 3-channel color images, they have a problem with applying to CNN. To solve this problem, we used each 1-channel grayscale image(Red, Blue, Green) that was separated from 3-channel color images. We were able to detect QFN solder defects by using this CNN. Later, further research is needed to detect other QFN.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.548-553
• /
• 2011

The lock-in thermography was employed to evaluate the defects in railway bogies. Prior to the actual application on railway bogies, in order to assess the detectability of known flaws, the calibration reference panel was prepared with various dimensions of artificial flaws. The panel was composed of polymer matrix composites, which were the same material with actual bogies. Through lock-in thermography evaluation, the optimal frequency of heat source was determined for the best flaw detection. Based on the defects information, the actual defect assessments on railway bogie were conducted with different types of railway bogies, which were used for the current operation. In summary, it was found that the novel infrared thermography technique could be an effective way for the inspection and the detection of surface defects on bogies since the infrared thermography method provided rapid and non-contact investigation of railway bogies.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1275-1278
• /
• 2003

This research describes a image-processing technique for the scratch detecting algorithm for ITO coated glass. The light emitter efficiency of Organic EL has a failing-off in quality due to many causes. One of the many causes was the defects of the surface in ITO coated glass. We use the logical level thresholding method for binarization of gray-scaled glass image. This method is useful to the algorithm for detecting scratch of ITO coated glass automatically without need of any prior information of manual fine tuning of parameters.

• Smart Media Journal
• /
• v.11 no.9
• /
• pp.47-55
• /
• 2022

Quality control in the smart factory manufacturing process is an important factor. Currently, quality inspection of home appliance manufacturing parts produced by the mold process is mostly performed with the naked eye of the operator, resulting in a high error rate of inspection. In order to improve the quality competition, an automatic defect detection system was designed and implemented. The proposed system acquires an image by photographing an object with a high-performance scan camera at a specific location, and reads defective products due to scratches, dents, and foreign substances according to the vision inspection algorithm. In this study, the depth-based branch decision algorithm (DBD) was developed to increase the recognition rate of defects due to scratches, and the accuracy was improved.

• Journal of the Semiconductor & Display Technology
• /
• v.11 no.3
• /
• pp.1-6
• /
• 2012

In this paper, inspection system based on optical scanning mechanism is designed and developed for solar cell wafer. It consists of optical scanning mechanism, NIR camera optics, machinery and control system, algorithm of defect detection and software. Optical scanning mechanism is composed of geometrical camera optics and structured hybrid illumination system. It is used to inspection of surface defects. NIR camera optics is used for inspection of defects inside solar cell wafer. It is shown that surface and internal micro defects can be detected in developed inspection system for solar cell wafer.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.45-59
• /
• 2023

Weakly supervised object localization (WSOL) is a task of localizing an object in an image using only image-level labels. Previous studies have followed the conventional class activation mapping (CAM) pipeline. However, we reveal the current CAM approach suffers from problems which cause original CAM could not capture the complete defects features. This work utilizes a convolutional neural network (CNN) pretrained on image-level labels to generate class activation maps in a multi-scale manner to highlight discriminative regions. Additionally, a vision transformer (ViT) pretrained was treated to produce multi-head attention maps as an auxiliary detector. By integrating the CNN-based CAMs and attention maps, our approach localizes defective regions without requiring bounding box or pixel-level supervision during training. We evaluate our approach on a dataset of apple images with only image-level labels of defect categories. Experiments demonstrate our proposed method aligns with several Object Detection models performance, hold a promise for improving localization.

• Journal of the Korean Society for Precision Engineering
• /
• v.29 no.1
• /
• pp.48-55
• /
• 2012

Pressure vessels in vehicle industries, power plants, and chemical industries are often affected by flaw and defect generated inside the pressure vessels due to production processes or being used. It is very important to detect such internal defects of pressure vessel because they sometimes bring out serious problems. In this paper, an optical defect detection method using digital shearography is used. This method has advantages that the inspection can be performed at a real time measurement and is less sensitive to environmental noise. Shearography is a laser-based technique for full-field, non-contacting measurement of surface deformation (displacement or strain). The ultimate goal of this paper is to detect flaws in pressure vessels and to measure the lengths of the flaws by using unwrapping, phase images which are only obtained by Phase map. Through this method, we could decrease post-processing (next processing). Real length of a pixel can be calculated by comparing minimum and maximum unwrapping images with shearing angle. Through measuring several specimen defects which have different lengths and depths of defect, it can be possible to interpret quantitatively by calculating gray level.

• Journal of Power System Engineering
• /
• v.14 no.4
• /
• pp.63-67
• /
• 2010

This paper introduces the eddy current signal characteristic of magnetic and non-magnetic gas turbine rotor. In the past, Magnetic particle inspection method was used in magnetic material for qualitative defect evaluation and the ultrasonic test method was used for quantitative evaluation. Nowadays, eddy current method is used in magnetic gas turbine rotor inspection due to advanced sensor design technology. We are studying on the magnetic gas turbine rotor by using eddy current method. We prepared diverse depth specimens made by magnetic and non-magnetic materials. We select optimum frequency according to material standard penetration data and experiment results. We got the signal on magnetic and non-magnetic material about 0.2 mm, 05 mm, 1.0 mm, 1.5 mm 2.0 mm and 2.5 mm depth defects and compare the signal amplitude and signal trend according to defect depth and frequency. The results show that signal amplitudes of magnetic are bigger than non-magnetic material and the trends are similar on every defect depth and frequency. The detection and resolution capabilities of eddy current are more effective in magnetic material than in non-magnetic materials. So, the eddy current method is effective inspection method on magnetic gas turbine rotor. And it has the merits of time saving and simple procedure by elimination of the ultrasonic inspection in traditional inspection method.

• Journal of the Korean Wood Science and Technology
• /
• v.31 no.2
• /
• pp.31-37
• /
• 2003

Among the nondestructive evaluation (NDE) methods for wood defect detection, ultrasonic wave has been considered as competitive technique in terms of economics and workability. Until now, researches on application of NDE methods for wood have focused mainly on standing tree and logs. Recently, some attempts have been conducted with NDE technique, for evaluation of wooden structural members. However, wooden structural members are different from others (standing tree or log) in various aspects. Expecially when some parts or whole member are covered with other materials, they can't be evaluated appropriately on general NDE methods. For the purpose of development of proper NDE technique for the wooden structural members, the ultrasonic wave transmission process investigated on artificial defect in wood. First, various types of transmission process were assumed, and then the transmission times were predicted respectively. Predicted times were compared with the measured time of ultrasonic wave and then a suitable type of transmission process is determined. In case of the ultrasonic wave doesn't transmit directly due to defect, it is reflected once only at the opposite surface of member, and the path is accord with the line of shortest length.

• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.803-812
• /
• 2019

Triplex composite is an epoxy-bonded joint structure, which constitutes the secondary barrier in a liquefied natural gas (LNG) carrier. Defects in the triplex composite weaken its shear strength and may cause leakage of the LNG, thus compromising the structural integrity of the LNG carrier. This paper proposes an autonomous triplex composite inspection (ATCI) system for visualizing and classifying hidden defects in the triplex composite installed inside an LNG carrier. First, heat energy is generated on the surface of the triplex composite using halogen lamps, and the corresponding heat response is measured by an infrared (IR) camera. Next, the region of interest (ROI) is traced and noise components are removed to minimize false indications of defects. After a defect is identified, it is classified as internal void or uncured adhesive and its size and shape are quantified and visualized, respectively. The proposed ATCI system allows the fully automated and contactless detection, classification, and quantification of hidden defects inside the triplex composite. The effectiveness of the proposed ATCI system is validated using the data obtained from actual triplex composite installed in an LNG carrier membrane system.