• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.21-22
• /
• 2023

딥러닝 모델은 영상 처리와 불량 감지 등 다양한 분야에서 높은 성능을 발휘하여 산업적으로 매우 중요하고 필수적인 기술이 되었다. 특히, 불량 감지는 제조업 분야에서 제품 품질 향상과 생산성 향상에 핵심적인 역할을 하는 기술로써 큰 관심을 받고 있다. 본 논문에서는 재건축 방식의 대표적인 모델인 DRAEM에 대해 불량 감지 성능을 향상하는 방법을 제시합니다. 이를 위해 컬러 분포의 차이를 최소화하는 손실 함수와 마스킹에 고주파 필터링을 적용하여 노이즈를 제거하는 방법을 활용한다. 이러한 방법들을 통해 DRAEM 모델의 성능을 개선하고, 정확하고 효과적인 불량 감지를 실현할 수 있다.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6043-6062
• /
• 2019

Low-rank matrix decomposition has shown its capability in many applications such as image in-painting, de-noising, background reconstruction and defect detection etc. In this paper, we consider the texture background of rail track images and the sparse foreground of the defects to construct a low-rank matrix decomposition model with block sparsity for defect inspection of rail tracks, which jointly minimizes the nuclear norm and the 2-1 norm. Similar to ADM, an alternative method is proposed in this study to solve the optimization problem. After image decomposition, the defect areas in the resulting low-rank image will form dark stripes that horizontally cross the entire image, indicating the preciselocations of the defects. Finally, a two-stage defect extraction method is proposed to locate the defect areas. The experimental results of the two datasets show that our algorithm achieved better performance compared with other methods.

• Journal of the Semiconductor & Display Technology
• /
• v.11 no.2
• /
• pp.45-51
• /
• 2012

Multilayer co-extrusion blown film construction is a popular technique for producing plastic films for various packaging industries. Automated detection of defective films can improve the quality of film production process. In this paper, we propose a film inspection system that can detect and classify film defects robustly. In our system, first, film images are acquired through a high speed line-scan camera under an appropriate lighting system. In order to detect and classify film defects, an inspection algorithm is developed. The algorithm divides the typical film defects into two groups: intensity-based and texture-based. Intensity-based defects are classified based on geometric features. Whereas, to classify texture-based defects, a texture analysis technique based on local binary pattern (LBP) is adopted. Experimental results revealed that our film inspection system is effective in detecting and classifying defects for the multilayer co-extrusion blown film construction line.

• Journal of Korea Multimedia Society
• /
• v.7 no.4
• /
• pp.451-458
• /
• 2004

A leather quality inspection by naked eyes has known as unreliable because of its biological characteristics like accumulated fatigue caused from an optical illusion and biological phenomenon. Therefore it is necessary to automate the leather quality inspection by computer vision technique. In this paper, we present automatic leather qua1ity classification system get information from leather surface. Leather is usually graded by its information such as texture density, types and distribution of defects. The presented algorithm explain how we analyze leather information like texture density and defects from the gray-level images obtained by digital camera. The density data is computed by its ratio of distribution area, width, and height of Fourier spectrum magnitude. And the defect information of leather surface can be obtained by histogram distribution of pixels which is Windowed from preprocessed images. The information for entire leather could be a standard for grading leather quality. The proposed leather inspection system using machine vision can also be applied to another field to substitute human eye inspection.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.363-366
• /
• 2001

The present process of grading leather quality by the rare eyes is not reliable. Because inconsistency of grading due to eyes strain for long time can cause incorrect result of grading. Therefore it is necessary to automate the process of grading quality of leather based on objective standard for it. In this paper, leather automatic classification system consists of the process obtaining the information of leather and the process grading the quality of leather from the information. Leather is graded by its information such as texture density, types and distribution of defects. This paper proposes the algorithm which sorts out leather information like texture density and defects from the gray-level images obtained by digital camera. The density information is sorted out by the distribution value of Fourier spectrum which comes out after original image is converted to the image in frequency domain. And the defect information is obtained by the statistics of pixels which is relevant to Window using searching Window after sort out boundary lines from preprocessed images. The information for entire leather is used as standard of grading leather quality, and the proposed algorithm is practically applied to machine vision system.

• Journal of Broadcast Engineering
• /
• v.18 no.4
• /
• pp.525-534
• /
• 2013

Recently, mura defect inspection techniques are receiving attention in LCD production procedure since demands of TFT-LCD are growing. In this paper, we propose an automatic mura defect inspection method using gabor wavelet transform and DCT. First, we generate a reference panel image using DCT based method. For original panel image and generated reference panel image, we apply a gabor wavelet transform to eliminate texture information in images. Then, we extract mura defect regions from the difference image between gabor wavelet transform image of original panel and generated reference panel image. Finally, all mura defect regions are quantified to detect accurate mura defects. Experimental results show that our method is more accurate and efficient than previous methods.

• Proceedings of the KIEE Conference
• /
• 1987.11a
• /
• pp.311-315
• /
• 1987

This paper describes the automatic visual inspect ion system of fabric defects based on pattern recognition techniques. To extract features for detection of fabric defects, four different techniques such as SGLDM. GCM, decorrelation method, and Laws' texture measure were investigated. From results of computer simulation, it has been found that GCM and decorrelation techniques provide good features. By employing a simple statistical pattern recognition technique, theaccuracy of classification of defect and nondefect was more than 90%. Some experimental results arm also presented.