• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4763-4775
• /
• 2020

This research aims to develop a deep learning-based method that automatically detects and segments the defects on railroad surfaces to reduce the cost of visual inspection of the railroad. We developed our segmentation model by modifying a fully convolutional network model [1], a well-known segmentation model used for machine learning, to detect and segment railroad surface defects. The data used in this research are images of the railroad surface with one or more defect regions. Railroad images were cropped to a suitable size, considering the long height and relatively narrow width of the images. They were also normalized based on the variance and mean of the data images. Using these images, the suggested model was trained to segment the defect regions. The proposed method showed promising results in the segmentation of defects. We consider that the proposed method can facilitate decision-making about railroad maintenance, and potentially be applied for other analyses.

• 한국정보시스템학회지:정보시스템연구
• /
• 제32권4호
• /
• pp.149-162
• /
• 2023

Purpose In the textile industry, fabric defects significantly impact product quality and consumer satisfaction. This research seeks to enhance defect detection by developing a transformer-based deep learning image segmentation model for learning high-dimensional image features, overcoming the limitations of traditional image classification methods. Design/methodology/approach This study utilizes the ZJU-Leaper dataset to develop a model for detecting defects in fabrics. The ZJU-Leaper dataset includes defects such as presses, stains, warps, and scratches across various fabric patterns. The dataset was built using the defect labeling and image files from ZJU-Leaper, and experiments were conducted with deep learning image segmentation models including Deeplabv3, SegformerB0, SegformerB1, and Dinov2. Findings The experimental results of this study indicate that the SegformerB1 model achieved the highest performance with an mIOU of 83.61% and a Pixel F1 Score of 81.84%. The SegformerB1 model excelled in sensitivity for detecting fabric defect areas compared to other models. Detailed analysis of its inferences showed accurate predictions of diverse defects, such as stains and fine scratches, within intricated fabric designs.

• 제어로봇시스템학회논문지
• /
• 제14권5호
• /
• pp.438-443
• /
• 2008

In this paper, segmenting and classifying low contrast defects on flat panel display is one of the key problems for automatic inspection system in practice. Problems become more complicated when the quality of acquired image is degraded by the illumination irregularity. Many algorithms are developed and implemented successfully for the defects segmentation. However, vision algorithms are inherently prone to be dependent on parameters to be set manually. In this paper, one morphological segmentation algorithm is chosen and a technique using frequency domain analysis of input images is developed for automatically selection the morphological parameter. An extensive statistical performance analysis is performed to compare the developed algorithms.

• Journal of Electrical Engineering and Technology
• /
• 제7권6호
• /
• pp.1001-1008
• /
• 2012

Non-destructive testing (NDT) is a technique used in science and industry to evaluate the properties of a material without causing damage. In this paper we propose a method for segmenting radiographic images of welding in order to extract the welding defects which may occur during the welding process. We study different methods of level set and choose the model adapted to our application. The methods presented here take the property of local segmentation geodesic active contours and have the ability to change the topology automatically. The computation time is considerably reduced after taking into account a new level set function which eliminates the re-initialization procedure. Satisfactory results are obtained after applying this algorithm both on synthetic and real images.

• Journal of the Korean Physical Society
• /
• 제73권11호
• /
• pp.1644-1649
• /
• 2018

Aiming at infrared thermal images with different buried depth defects, we study a variety of image segmentation algorithms based on the threshold to develop global search ability and the ability to find the defect area accurately. Firstly, the iterative thresholding method, the maximum entropy method, the minimum error method, the Ostu method and the minimum skewness method are applied to image segmentation of the same infrared thermal image. The study shows that the maximum entropy method and the minimum error method have strong global search capability and can simultaneously extract defects at different depths. However none of these five methods can accurately calculate the defect area at different depths. In order to solve this problem, we put forward a strategy of "divide and conquer". The infrared thermal image is divided into several local thermal maps, with each map containing only one defect, and the defect area is calculated after local image processing of the different buried defects one by one. The results show that, under the "divide and conquer" strategy, the iterative threshold method and the Ostu method have the advantage of high precision and can accurately extract the area of different defects at different depths, with an error of less than 5%.

• 한국멀티미디어학회논문지
• /
• 제15권2호
• /
• pp.204-214
• /
• 2012

본 논문은 비전장비의 결함 검사 시스템을 위한 불균일한 휘도분포를 가지는 TFT-LCD 영상에서 결함 영역을 분할하는 방법을 다룬다. 불균일한 휘도분포 때문에 결함의 영역을 찾기 어려우며 이를 위해 많은 방법들이 제안되었다. Kamel과 Zhoa는 문자 및 그래픽의 분할을 위해 논리적 단계화 방법을 제안하였고, 이 방법은 공간상에서 수행되어지는 지역적 분할 방법으로 불균일한 분포 상에서도 문자가 잘 분할되는 장점이 있다. TFT-LCD의 저해상도 영상도 배경의 분포가 불균일하여 본 논문에서는 Kamel과 Zhoa의 방법을 답습하여 새로운 결함 영역 분할 방법을 제안한다. 제안한 방법은 결함주위에 발생하는 과검출(Ghost object)이 적은 장점이 있으며 제안 방법의 성능을 증명하기위해 실제 결함이 존재하는 TFT-LCD 영상을 이용하여 실험하고, 주파수상에서 많이 사용되는 FFT의 밴드패스 필터를 이용한 분할 방법과 비교하였다.

• 한국정보과학회논문지:데이타베이스
• /
• 제34권2호
• /
• pp.99-108
• /
• 2007

본 논문에서는 TFT-LCD에 사용되는 편광 필름(polarized film)의 제작 과정 중 최종 단계에서 수행되는 필름의 결함 검출 및 결함 유형을 판정하기 위한 필름 결함 검출 시스템(Film Defect Inspection System: FDIS)을 설계하고 이를 구현하였다. 제안한 시스템은 영상 세그멘테이션 기법을 이용하여 편광 필름 영상으로부터 결함을 검출하였고, 검출된 결함의 영상을 분석하여 결함 유형을 판정할 수 있도록 설계되었다. 결함 유형의 판정은 결함 영역의 형태적 특성 및 질감(texture) 등의 특징을 추출하여 템플리트(template) 데이타베이스에 저장된 기준(reference) 결함 영상과 비교함으로써 수행된다. FDIS를 이용한 실험 결과, 테스트 영상에서 모든 결함 영역을 빠른 시간 안에 (평균 0.64초), 정확히 검출하였으며(Precision 1.0, Recall 1.0), 결함 유형을 판정하는 실험에서도 평균 Precision 0.96, Recall 0.95로 정확도가 매우 높은 것을 관찰할 수 있었다. 또한 회전 변형을 적용한 경우의 결함 유형 검출 실험에서도 평균 Precision 0.95, Recall 0.89로 제안한 기법이 회전 변환에 대하여 견고함을 보여 주었다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.1101-1104
• /
• 1995

Through welding fabrication, user can feel an surficaial and capable unsatisfaction because of welded defects, Generally speaking, these are called weld defects. For checking these defects effectively without time loss effectively, weldability estimation system setup isan urgent thing for detecting whole specimen quality. In this study, by laser vision camera, catching a rawdata on welded specimen profiles, treating vision processing with these data, qualititative defects are estimated from getting these information at first. At the same time, for detecting quantitative defects, whole specimen weldability estimation is pursued by multifeature pattern recognition, which is a kind of fuzzy pattern recognition. For user friendly, by weldability estimation results are shown each profiles, final reports and visual graphics method, user can easily determined weldability. By applying these system to welding fabrication, these technologies are contribution to on-line weldability estimation.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.57.4-57
• /
• 2002

$\textbullet$ Image segmentation is an essential technique of image analysis. In spite of the traditional issues in contour initialization and boundary concavities, active contour models(snakes) are popular and known as successful methods for segmentation. $\textbullet$ We could find in experiment that snake using Gaussian External Force is fast in time but low in accuracy and snake using Gradient Vector Flow by Chenyang Xu and Jerry L. Prince is high in accuracy but slow in time. $\textbullet$ In this paper, we presented a new active contour model, GGF snake, for segmentation of endoscopic image. Proposed GGF snake made up for the defects of the traditional snakes in contour initialization and boundary...

• 한국공작기계학회논문집
• /
• 제16권4호
• /
• pp.22-28
• /
• 2007

The welded defects are usually called user's unsatisfaction for appearance and functional usage. For checking these defects effectively without time loss, setup of weldability estimation system is an important for detecting whole specimen quality. In this study, after catching a rawdata on welded specimen profiles and treating vision processing with these data, the qualitative defects are estimated from getting these information by laser vision camera at first. At the same time, the weldability estimation for whole specimen is produced. For user friendly, the weldability estimation results are shown each profiles, final reports and visual graphics method. So, user can easily determined weldability. By applying these system to welding fabrication, these technologies are contribution to on-line setup of weldability estimation system.