• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Nuclear Engineering and Technology
• /
• v.52 no.4
• /
• pp.856-862
• /
• 2020

Defect inspection system for industrial applications takes the important portion. Non-destructive inspection method has been significantly improved. Infrared thermography, as one of method for non-destructive inspection, can provide relatively precise data and quick inspection time. This study, it was performed to measure defect according to the measurement limit of the non-visible areas such as the back surface of the pipe using reflection plate using reflection plate based on Infrared thermography. The materials of the reflection plate were determined in consideration of the space limitation and the thermal characteristics, and defects were detected by the manufactured reflection plate. Detection of defect in non-visible area using the candidate materials for reflection plate was conducted.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.499-506
• /
• 2004

The copper foil surface inspection system is necessary for the factory automation and product quality. The developed system is composed of the high speed line scan camera, the image capture board and the processing computer. For the system resource utilization and real-time processing, multi-threaded architecture is introduced. There are one image capture thread, 2 or more defect detection threads, and one defect communication thread. To process the high-speed input image data, the I/O overlap is used through the double buffering. The defect is first detected by the predetermined threshold. To cope with the light irregularity, the compensation process is applied. After defect detection, defect type is classified with the defect width, eigenvalue ratio of the defect covariance matrix and gray level of defect. In experiment, for high-speed input image data, real-time processing is possible with multi -threaded architecture, and the 89.4% of the total 141 defects correctly classified.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2007.06a
• /
• pp.351-352
• /
• 2007

• Nuclear Engineering and Technology
• /
• v.39 no.5
• /
• pp.637-646
• /
• 2007

An UET (ultrasound excited thermography) has been used for several years for a remote non-destructive testing in the automotive and aircraft industry. It provides a thermo sonic image for a defect detection. A thermograhy is based On a propagation and a reflection of a thermal wave, which is launched from the surface into the inspected sample by an absorption of a modulated radiation. For an energy deposition to a sample, the UET uses an ultrasound excited vibration energy as an internal heat source. In this paper the applicability of the UET for a realtime defect detection is described. Measurements were performed on two kinds of pipes made from a copper and a CFRP material. In the interior of the CFRP pipe (70mm diameter), a groove (width - 6mm, depth - 2.7mm, and length - 70mm) was engraved by a milling. In the case of the copper pipe, a defect was made with a groove (width - 2mm, depth - 1mm, and length - 110 mm) by the same method. An ultrasonic vibration energy of a pulsed type is injected into the exterior side of the pipe. A hot spot, which is a small area around the defect was considerably heated up when compared to the other intact areas, was observed. A test On a damaged copper pipe produced a thermo sonic image, which was an excellent image contrast when compared to a CFRP pipe. Test on a CFRP pipe with a subsurface defect revealed a thermo sonic image at the groove position which was a relatively weak contrast.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.7
• /
• pp.865-870
• /
• 2018

A machine vision based industrial inspection includes defects detection and classification. Fast inspection is a fundamental problem for many applications of real-time vision systems. It requires little computation time and localizing defects robustly with high accuracy. Deep learning technique have been known not to be suitable for real-time applications. Recently a couple of fast region-based CNN algorithms for object detection are introduced, such as Faster R-CNN, and YOLOv2. We apply these methods for an industrial inspection problem. Three CNN based detection algorithms, VOV based CNN, Faster R-CNN, and YOLOv2, are experimented for defect detection on metal surface. The results for inspection time and various performance indices are compared and analysed.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1996.03a
• /
• pp.24-29
• /
• 1996

The seniconductor, which is precision product, requires many inspection processes. The surface conditions of the semiconductor chip effect on the functions of the semiconductors. The defects of the chip surface is crack or void. Because general inspection method requires many inspection processes, the inspection system which searches immediately and preciselythe defects of the semiconductor chip surface. We propose the inspection method by using the computer vision system. This study presents an image processing algorithm for inspecting the surface defects(crack, void)of the semiconductor test samples. The proposed image processing algorithm aims to reduce inspection time, and to analyze those experienced operator. This paper regards the chip surface as random texture, and deals with the image modeling of randon texture image for searching the surface defects. For texture modeling, we consider the relation of a pixel and neighborhood pixels as noncasul model and extract the statistical characteristics from the radom texture field by using the 2D AR model(Aut oregressive). This paper regards on image as the output of linear system, and considers the fidelity or intelligibility criteria for measuring the quality of an image or the performance of the processing techinque. This study utilizes the variance of prediction error which is computed by substituting the gary level of pixel of another texture field into the two dimensional AR(autoregressive model)model fitted to the texture field, estimate the parameter us-ing the PAA(parameter adaptation algorithm) and design the defect detection filter. Later, we next try to study the defect detection search algorithm.

• Journal of Power System Engineering
• /
• v.8 no.3
• /
• pp.52-57
• /
• 2004

A new non-destructive inspection technique has been developed. One characteristic of the technique is that defects are visualized by laser ray. Magnetic domains and domain walls of a magneto-optical sensor(MO sensor) are varied by the magnetic flux leaked by defects, and the variations are observed by the reflected light of the laser ray. The information of defect can remotely be inspected by this technique in a real time. This paper describes the results estimated on the 2-dimensional surface defects and opposite-side defects in a ferromagnetic material and the natural surface defect in a clutch disk wheel. The light region of a visible image and the magnitude of a reflected light increases as the input current of the magnetizer increases. The natural surface defect, that has not the width of crack's open mouth, can be also visualized like as 2-dimensional artificial defects.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.11
• /
• pp.55-61
• /
• 2009

The wall thinning defect of nuclear power pipe is mainly occurred by the affect of the flow accelerated corrosion (FAC) of fluid. This type of defect becomes the cause of damage or destruction of in carbon steel pipes. Therefore, it is very important to measure defect which is existed not only on the welding part but also on the whole field of pipe. This study use dual-beam Shearography, which can measure the out-of-plane deformation and the in-plane deformation by using another illuminated laser beam and simple image processing technique. And this study proposes Infrared thermography, which is a two-dimensional non-contact nondestructive evaluation that can detect internal defects from the thermal distribution by the inspection of infrared light radiated from the object surface. In this paper, defect of nuclear power pipe were, measured using dual-beam shearography and infrared thermography, quantitatively evaluated by the analysis of phase map and thermal image pattern.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.1353-1356
• /
• 2004

In recent year, OLED(organic light emitted display) is used as the next generation device of FPD. OLED have been replacing the flat panel display device such as LCD, STN-LCD and TFT because this device is more efficient, economic and simple than those FPD devices, and this need not backlight system for visualization. The performance and efficiency of OLED is related with surface defect of ITO coated glass substrate. The typical surface defect of glass substrate is nonuniformity and bad surface roughness. ITO coated glass substrate is destroied for inspection about surface roughness and non-uniformity. Generally detection of the defects in the surface for ITO coated glass substrate is dependent on operator's experience. In this research, relationship between working parameter and surface non-uniformity is studied using regression analysis.