• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.4
• /
• pp.365-384
• /
• 2024

The development of scanning technology is accelerating for safer and more efficient automated inspection than human-based inspection. Research on automatically detecting facility damage from images collected using computer vision technology is also increasing. The pixel size, quality, and quantity of an image can affect the performance of deep learning or image processing for automatic damage detection. This study is a basic to acquire high-quality raw image data and camera performance of a mobile tunnel scanning system for automatic detection of damage based on deep learning, and proposes a method to quantitatively evaluate image quality. A test chart was attached to a panel device capable of simulating a moving speed of 40 km/h, and an indoor test was performed using the international standard ISO 12233 method. Existing image quality evaluation methods were applied to evaluate the quality of images obtained in indoor experiments. It was determined that the shutter speed of the camera is closely related to the motion blur that occurs in the image. Modulation transfer function (MTF), one of the image quality evaluation method, can objectively evaluate image quality and was judged to be consistent with visual observation.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.3
• /
• pp.254-259
• /
• 2014

A pressurized heavy water reactor (PHWR) core has 380 fuel channels contained and supported by a horizontal cylindrical vessel known as the calandria, whereas a pressurized water reactor (PWR) has only a single reactor vessel. The pressure tube, which is a pressure-retaining component, has a 103.4 mm inside diameter ${\times}$ 4.19 mm wall thickness, and is 6.36 m long, made of a zirconium alloy (Zr-2.5 wt% Nb). This provides support for the fuel while transporting the $D_2O$ heat-transfer fluid. The simple tubular geometry invites highly automated inspection, and good approach for all inspection. Similar to all nuclear heat-transfer pressure boundaries, the PHWR pressure tube requires a rigorous, periodic inspection to assess the reactor integrity in accordance with the Korea Nuclear Safety Committee law. Volumetric-based nondestructive evaluation (NDE) techniques utilizing ultrasonic and eddy current testing have been adopted for use in the periodic inspection of the fuel channel. The eddy current testing, as a supplemental NDE method to ultrasonic testing, is used to confirm the flaws primarily detected through ultrasonic testing, however, eddy current testing offers a significant advantage in that its ability to detect surface flaws is superior to that of ultrasonic testing. In this paper, effectiveness of flaw detection and the depth sizing capability by eddy current testing for the inside surface of a pressure tube, will be introduced. As a result of this examination, the ET technique is found to be useful only as a detection technique for defects because it can detect fine defects on the surface with high resolution. However, the ET technique is not recommended for use as a depth sizing method because it has a large degree of error for depth sizing.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.10
• /
• pp.887-895
• /
• 2013

Metastatic bone cancer, the cancer which occurred in the various organs and progressively spread to bone, is one of the complications in cancer patients. This cancer is divided into the osteoblast and osteolytic metastasis. Although Computer Tomography(CT) could be an useful tool in diagnosis of bone metastasis, lesions are often missed by the visual inspection and it makes clinicians difficult to detect metastasis earlier. Therefore, in this study, we construct a three-dimensional(3D) volume rendering data from tomography images of the chest CT, and apply a 3D based image processing algorithm to them for detection bone metastasis lesions. Then we perform a three-dimensional visualization of the detected lesions.From our test using 10 clinical cases, we confirmed 94.1% of average sensitivity for osteoblast, and 90.0% of average sensitivity, respectively. Consequently, our findings showed a promising possibility and potential usefulness in diagnosis of metastastic bone cancer.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2568-2574
• /
• 2011

31 December 2012 will be the end of terrestrial analog broadcasting. Digital broadcasting will begin. The picture quality on analog broadcasting, was not a problem. but, In digital broadcasting, is a problem. Service for streaming on the digital broadcasting MPEG video compression. And the content is added block noise. These block noise measured by people's eyes. but, people's eyes is subjective. In this paper, the on-reference methods to detect block noise. And detected by measuring the distribution of block noise, to quantify the levels of block-noise. With this study, block noise by visual inspection using an automated tool, by being objective measure of information and communication will contribute to the development of the video.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.3 no.2
• /
• pp.136-141
• /
• 2011

The current tendency on development and change of equipment system in the factory are overlapped with the specific field of the existing systems such as PLC, DCS and SCADA, and the limited portion of the systems in the specific field stands in their own field. Specially, systematic integration, inspection control system and manufacturing management system, management information system are getting closely linked and therefore we increasingly need the open system. Meeting the needs, manufacturing automated equipments in the factory overcoming the shortcomings of unlinked unit equipment recently are getting changed to the phase closely linking with other systems. The training systems for the university, however, have not kept up with the needs from the industry, in spite that fused complex function and performance are asked in the field. To solve the problems, we suggest that the training courses and the equipment designed for the undergraduate education.

• Korean Journal of Optics and Photonics
• /
• v.15 no.6
• /
• pp.583-590
• /
• 2004

The autofocus is one of the important processes in the automated vision inspection or measurements using optical microscopes, because it influences the measuring accuracy. In this paper, we used the confocal microscope configuration based on not a pinhole but a single-mode optical fiber. A single mode fiber has the functions of source and detector by applying the reciprocal scheme. As a result, we acquired a simple system configuration and easy alignment of the optical axis. Also, we embodied a fast autofocus system by acquiring the focus error signal through a source modulation technique. The source modulation technique can effectively reduce physical disturbances compared with objective lens modulation, and it is easily applicable to general optical microscopes. The focus error signal was measured with respect to the modulation amplitude, reflectance of the specimen and inclination angle of the measuring surface. The performance of the proposed autofocus system was verified through autofocusing flat mirror surface. In addition, we confirmed that source modulation rarely degrades the depth resolution by the comparison between the FWHMs of axial response curves.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.28 no.1
• /
• pp.46-53
• /
• 2008

Ultrasonic C-scan technique is one of very popular techniques being used for detection of flaws in polymer matrix composite(PMC). However, the application of this technique is very limited for evaluation of defects in PMC fabricated by the automated fiber placement process. The purpose of this study is to develop a novel ultrasonic hybrid system based on nondestructive and non-contact ultrasonic techniques for evaluation of delamination in carbon/epoxy and carbon/PPS composite laminates. It was shown that the newly developed ultrasonic hybrid system based on dual air-coupled pitch-catch technique with ultrasonic scattering reflection concept could provide excellent image with higher resolution of delamination in PMC compared with the conventional pitch-catch method. It is expected that this ultrasonic hybrid technique can be applied for on-line inspection of flaws in PMC during the fabrication process.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.7
• /
• pp.7-15
• /
• 2020

Recently, the fourth industrial revolution has been presented as a new paradigm and additive manufacturing (AM) has become one of the most important topics. For this reason, process monitoring for each cross-sectional layer of additive metal manufacturing is important. Particularly, deep learning can train a machine to analyze, optimize, and repair defects. In this paper, image classification is proposed by learning images of defects in the metal cross sections using the convolution neural network (CNN) image labeling algorithm. Defects were classified into three categories: crack, porosity, and hole. To overcome a lack-of-data problem, the amount of learning data was augmented using a data augmentation algorithm. This augmentation algorithm can transform an image to 180 images, increasing the learning accuracy. The number of training and validation images was 25,920 (80 %) and 6,480 (20 %), respectively. An optimized case with a combination of fully connected layers, an optimizer, and a loss function, showed that the model accuracy was 99.7 % and had a success rate of 97.8 % for 180 test images. In conclusion, image labeling was successfully performed and it is expected to be applied to automated AM process inspection and repair systems in the future.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.29 no.3
• /
• pp.235-241
• /
• 2009

Composite wood materials are very sensitive to water and inspection without any coupling medium of a liquid is really needed to wood materials due to the permeation of coupling medium such as water. However, air-coupled ultrasound has obvious advantages over water-coupled experimentation compared with conventional C-scanner. In this work, it is desirable to perform contact-less nondestructive evaluation to assess wood material homogeneity. A wood material was nondestructively characterized with non-contact and contact modes to measure ultrasonic velocity using automated data acquisition software. We have utilized a proposed peak-delay measurement method. Also through transmission mode was performed because of the main limitation for air-coupled transducers, which is the acoustic impedance mismatch between most materials and air. The variation of ultrasonic velocity was found to be somewhat difference due to air-coupled limitations over conventional scan images. However, conventional C-scan images are well agreed with increasing the resin-infiltrated time as expected. Finally, we have developed a measurement system of an ultrasonic velocity based on data acquisition software for obtaining ultrasonic quantitative data for correlation with C-scan images.

• Journal of Digital Convergence
• /
• v.14 no.8
• /
• pp.305-311
• /
• 2016

If the automated image calibration system is performed in the position of non-experts, an expert will be required in every case inefficiently. But this requires an expert only when absolutely necessary. As well as the rapid system operation and efficient workforce can be managed. Image correction to perform projector inspection and management skills and to filter SW plug-in correction is that special theater system maintenance is not only managed efficiently, but also combined image analysis techniques can improve the technical perfection. This paper is to minimize the economic loss by developing a 10-bit High-depth and high-resolution $360^{\circ}$ projection image analysis technique and is to development of the special theater calibration system to effectively support quality.