• Journal of the Korean Society for Nondestructive Testing
• /
• v.37 no.2
• /
• pp.106-114
• /
• 2017

This paper presents an automated subsurface micro void detection technique based on pulsed infrared thermography for inspecting epoxy molding compounds (EMC) used in electronic device packaging. Subsurface micro voids are first detected and visualized by extracting a lock-in amplitude image from raw thermal images. Binary imaging follows to achieve better visualization of subsurface micro voids. A median filter is then applied for removing sparse noise components. The performance of the proposed technique is tested using 36 EMC samples, which have subsurface (below $150{\mu}m{\sim}300{\mu}m$ from the inspection surface) micro voids ($150{\mu}m{\sim}300{\mu}m$ in diameter). The experimental results show that the subsurface micro voids can be successfully detected without causing any damage to the EMC samples, making it suitable for automated online inspection.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.32 no.2
• /
• pp.11-19
• /
• 2024

Flight simulators are crucial devices for aircraft piloting training and simulation, requiring regular inspections to maintain performance and operational quality. This study explores the development of an automated inspection system for flight simulators to automate quality inspections of control loading systems (CLS). While quality inspection of the control loading system (CLS) is essential for flight simulators, manual inspections are common practice. To address this, we developed an Auto Qualification Test Guide (Auto QTG) using artificial control logic and sensor data and applied it to the militarily simulator. Experimental results demonstrate that Auto QTG successfully automates quality inspections of CLS, enhancing accuracy and efficiency. This automated inspection system is expected to contribute to improving the operation and maintenance of flight simulators.

• Journal of Platform Technology
• /
• v.11 no.6
• /
• pp.13-20
• /
• 2023

Regularly inspecting vehicle tires' condition is imperative for driving safety and comfort. Poorly maintained tires can pose fatal risks, leading to accidents. Unfortunately, manual tire visual inspections are often considered no less laborious than employing an automatic tire inspection system. Nevertheless, an automated tire inspection method can significantly enhance driver compliance and awareness, encouraging routine checks. Therefore, there is an urgency for automated tire inspection solutions. Here, we focus on developing a deep learning (DL) model to predict cracked tires. The main idea of this study is to demonstrate the comparative analysis of DenseNet121, VGG-19 and EfficientNet Convolution Neural Network-based (CNN) Transfer Learning (TL) and suggest which model is more recommended for cracked tire classification tasks. To measure the model's effectiveness, we experimented using a publicly accessible dataset of 1028 images categorized into two classes. Our experimental results obtain good performance in terms of accuracy, with 0.9515. This shows that the model is reliable even though it works on a dataset of tire images which are characterized by homogeneous color intensity.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.5
• /
• pp.162-165
• /
• 2007

TFT-LCD process has two advantages as compared with the semiconductor-process. It is that cycle time is short and number of the final products are small. But it needs complicated inspection / assembly line to be treated manually and much higher labor costs in the TFT-LCD process. Also, It is necessary to build PICS(Production Information and Control System) which is automated and intelligent. In this paper, an automated process of LCD module assembly line that can increase productivity and reduce the cost of production to strengthen the competitiveness corresponding with global market is planned in comparison with its manual/semi-auto. It is noted that The automated line for COG$\sim$FOG process replacing with the existing facilities had the following effects; the productivity is increased to about 1.5 times and labor cost reduced 85%. In addition, whole assembly line can be short and simple.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.139-142
• /
• 2000

$\mu$BGA(Ball Grid Array) is growing in response to a great demand for smaller and lighter packages for the use in laptop, mobile phones and other evolving products. However it is not easy to find its defect by human visual due to in very small dimension. From this point of view, we are interested its development of a vision based automated inspection algorithm. For this, first a 2D view of $\mu$BGA is described under a special blue illumination. Second, a notation-invariant 2D inspection algorithm is developed. Finally a 3D inspection algorithm is proposed for the case of stereo vision system. As a simulation result, it is shown that 3D defect not easy to find by 2D algorithm can be detected by the proposed inspection algorithm.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1783-1786
• /
• 2003

In this paper, an automated line-defect detection method for TFT-LCD panel is presented. A DFB(Directional Filter Bank) and line-projection method are used to find line-defect which is one of the major defects occurred in TFT-LCD panel. The experimental results show that the proposed algorithm gave promising results for applying automated inspection technique for TFT-LCD panel.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.4 no.2
• /
• pp.91-97
• /
• 2012

The automated visual inspection system (machine vision system) for quality assurance is an important factory automation equipment in the manufacturing industries, such as display, semiconductor, etc. The world market of the machine vision components is expected 18 billon dollars in 2015. Therefore, there is a lot of demand for the machine vision engineers. However, there are no technical training courses for machine vision technologies in vocational schools, colleges and universities. In this paper, we propose a technical training program for the machine vision technology. The total time of training is 30 to 60 hours and the training program can operate flexibly by student's major, a priori knowledge and education level.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.1-15
• /
• 2009

In this paper, we have proposed an automated system that accurately measures the thickness and unbalanced wear of brake shoes, and the distance between brake shoes and wheels for travelling rolling stock. The images of brake shoes are captured automatically while rolling stock is passing by an inspection station. And in order to measure the thickness, etc. the locations of brake shoes are first determined because the locations are not the same in the captured image. Toward this goal, shadow regions between the brake shoes and wheels are utilized that are common in all captured images. The boundary of the shadow regions is modeled by an second order polynomial, and constrained curve fitting method is adopted to detect a curve (the initial curve) that passes through the regions. Then, three curves that correspond to the front, back of brake shoes and wheels, and a line that passes through the vertical surface of brake shoes are detected using the initial curve and intensity change information. Finally, the thickness, etc. are calculated using the detected curves and line, and experimental results showed that the brake shoe thickness was measured with an accuracy of 0.654mm.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.84-88
• /
• 2023

This study proposes an automated tilt measurement method using point cloud for buildings. The proposed method consists of two main steps: 1) exterior wall plane extraction, and 2) edge estimation and angle calculation. To validate the performance of the proposed method, the algorithm is applied to a target building, of which the estimated tilt values are compared with those obtained from a total station, a commonly used tool for tilt measurement. The result shows that most estimated tilt values are within the maximum and minimum ranges of the total station measurement, suggesting that the proposed algorithm provides sufficient measurement accuracy. Furthermore, the proposed method is shown to be automated and reliable as well as free from human-induced errors compared to the total station.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.1
• /
• pp.1-11
• /
• 1997

Austomated visual inspection(AVI) capability has become an important key component in the automated manufacturing system. In such a visual inspection system an intensity(or color) image of a scene is quickly affected by optical property of objects, condition and roughness of surface, lens and filters, image sensor property and lighting system. In particular, the lighting system disign is the most important factor, since it affects overall performance of the visual system. For fast and cheap automated visual inspection system it is important to obtain the good image quality which results from careful attention to the design of the lighting system. In this paper, the lighting subsystem of AVI system is analysed for the inspection of printed circuit board(PCB) patterns. The spectral reflectance of materials, which are composed of PCB, is measured for choosing the light source. The reflection property is theoretically obtained by a reflection model and also obtained by experiments which measure intensity with varying the viewing direction of image sensor and the lighting direction of illuminator. The illumination uniformity of a ring-type illuminator. The lighting system is designed based upon the experimental results and theoretial analysis.