• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.431-433
• /
• 2006

The goal of this paper is improvement of vision inspection accuracy by using histogram specification operation. The histogram is composed of horizontal axis of image intensity value and vertical axis of pixel number in image. In appearance vision inspection, the histogram of reference image and input image are different because of minutely lighting distinction. The minutely lighting distinction is main reason of vision inspection error in many cases. Therefore we made an effort for elevation of vision inspection accuracy by making the identical histogram of reference image and input image. As a result of this area separation histogram specification algorithm, we could increase the exactness of vision inspection and prevent system error from physical and spirit condition of human. Also this system has been developed only using PC, CCD Camera and Visual C++ for universal workplace.

• 한국공작기계학회논문집
• /
• 제16권5호
• /
• pp.157-161
• /
• 2007

There are technological changes to reduce the size and weight of electronic components and to accommodate multi-functions in them. To meet this trend, more complicated technological processes are required. To maintain the processes, more accurate inspection systems are also necessary. Therefore, new inspection methods are needed, which is differ from conventional inspection methods such as electrical test methods ICT(In-Circuit Test), FCT(Function Test) and visual test using optical equipments. One of the possible approaches is non-destructive test using X-ray. In this paper, an inspection method using X-ray is developed and applied to inspection of soldering state and internal defects of electronic components.

• 천문학회보
• /
• 제39권1호
• /
• pp.40.1-40.1
• /
• 2014

We have classified barred galaxies for 418 RC3 sample galaxies within z < 0.01 from SDSS DR7 using the visual inspection, ellipse fitting method and Fourier analysis. We found the bar fraction to be ~60%, 43% and 70% for each method and that the ellipse fitting method tends to miss the bar when a large bulge hides the transition from bar to disk in early spirals. We also confirmed that the Fourier analysis cannot distinguish between a bar and spiral arm structure. These systematic difficulties may have produced the long-time controversy about bar fraction dependence on Hubble sequence, mass and color. We designed a new method to fine bars by analyzing the ratio map of bar strength in polar coordinates, which yields the bar fraction of ~27% and ~32% for SAB and SB, respectively. The consistency with visual inspection reaches around 70%, and roughly 90% of visual strong bar are classified as SAB and SB in our classification. Although our method also has a weakness that a large bulge lowers the value of bar strength, the missing bar fraction in early spirals is reduced to the level of ~1/4 compared to the ellipse fitting method. Our method can make up for the demerits of the previous automatic classifications and provide a quantitative bar classification that agrees with visual classification.

• 한국생산제조학회지
• /
• 제22권1호
• /
• pp.150-155
• /
• 2013

This work present a new method of sealing inspection system for vehicle in which foam rubber materials are used for sealing the vehicle parts. This system is composed from a devices comprising non-contact and real-time scanning on visual inspection in machine parts. We have been investigated qualitative factors that influenced on sealing system of vehicle structure which flexibly attenuated vibration and plenty of foam rubber materials having elastic property. However, there are different factors which still depended on outdated technique (personnel subjective judgment) in the performance inspection of rubber parts, specially for cross section inspection. Through a newly developed inspection system which recently applied for the production line, we successfully achieved more effective results of matching rate by about 80 % in the sealing performance inspection with 0.7% to 1.4% in the repeated errors. These are resulted from non-contacted response by CCD camera and vision program using geometry matching method. We expect that this system may be widely applied in the strict inspection parts of more diverse cross-section in future.

• Korean Journal of Radiology
• /
• 제19권6호
• /
• pp.1053-1065
• /
• 2018

Objective: To evaluate the clinical impact of using registration software for ablative margin assessment on pre-radiofrequency ablation (RFA) magnetic resonance imaging (MRI) and post-RFA computed tomography (CT) compared with the conventional side-by-side MR-CT visual comparison. Materials and Methods: In this Institutional Review Board-approved prospective study, 68 patients with 88 hepatocellulcar carcinomas (HCCs) who had undergone pre-RFA MRI were enrolled. Informed consent was obtained from all patients. Pre-RFA MRI and post-RFA CT images were analyzed to evaluate the presence of a sufficient safety margin (${\geq}3mm$) in two separate sessions using either side-by-side visual comparison or non-rigid registration software. Patients with an insufficient ablative margin on either one or both methods underwent additional treatment depending on the technical feasibility and patient's condition. Then, ablative margins were re-assessed using both methods. Local tumor progression (LTP) rates were compared between the sufficient and insufficient margin groups in each method. Results: The two methods showed 14.8% (13/88) discordance in estimating sufficient ablative margins. On registration software-assisted inspection, patients with insufficient ablative margins showed a significantly higher 5-year LTP rate than those with sufficient ablative margins (66.7% vs. 27.0%, p = 0.004). However, classification by visual inspection alone did not reveal a significant difference in 5-year LTP between the two groups (28.6% vs. 30.5%, p = 0.79). Conclusion: Registration software provided better ablative margin assessment than did visual inspection in patients with HCCs who had undergone pre-RFA MRI and post-RFA CT for prediction of LTP after RFA and may provide more precise risk stratification of those who are treated with RFA.

• Smart Structures and Systems
• /
• 제33권1호
• /
• pp.55-64
• /
• 2024

This paper proposes a fusion imaging-based coating-defect classification method for steel structures that uses zero-shot learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured by an infrared (IR) camera, while photos of the coating surface are captured by a charge-coupled device (CCD) camera. The measured heat responses and visual images are then analyzed using zero-shot learning to classify the coating defects, and the estimated coating defects are visualized throughout the inspection surface of the steel structure. In contrast to older approaches to coating-defect classification that relied on visual inspection and were limited to surface defects, and older artificial neural network (ANN)-based methods that required large amounts of data for training and validation, the proposed method accurately classifies both internal and external defects and can classify coating defects for unobserved classes that are not included in the training. Additionally, the proposed model easily learns about additional classifying conditions, making it simple to add classes for problems of interest and field application. Based on the results of validation via field testing, the defect-type classification performance is improved 22.7% of accuracy by fusing visual and thermal imaging compared to using only a visual dataset. Furthermore, the classification accuracy of the proposed method on a test dataset with only trained classes is validated to be 100%. With word-embedding vectors for the labels of untrained classes, the classification accuracy of the proposed method is 86.4%.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2007년도 정기 학술대회 논문집
• /
• pp.90-95
• /
• 2007

Conventional bridge inspection involves the physical positioning of an inspector by the hydraulic telescoping boom of a "snooper truck" thereby providing visual access to bridge components. The process is time consuming, hazardous, and may be affected by lighting conditions, Therefore, it is of great interest that an automated and/or teleoperated inspection robot be developed to replace the manual inspection procedure. This paper describes the advanced bridge inspection robot system under development and other related activities currently undergoing at the Bridge Inspection Robot Development Interface (BIRDI). BIRDI is a research consortium with its home in the Department of Civil and Environmental System Engineering at Hanyang University at Ansan. Its primary goal is to develop advanced robot systems for bridge inspection and monitoring for immediate field application and commercialization. The research program includes research areas such as advanced inspection robot and motion control system, sensing technologies for monitoring and assessment, and integrated system for bridge maintenance. The center embraces 12 institutions, which consist of 7 universities, 2 research institutes, and 3 private enterprises. Research projects are cross-disciplinary and include experts from structural engineering, mechanical engineering, electronic and control engineering. This research project will contribute to advancement of infrastructure maintenance technology, enhancement of construction industry competitiveness, and promotion of national capacity for technology innovation.

• 제어로봇시스템학회논문지
• /
• 제20권10호
• /
• pp.1030-1035
• /
• 2014

Machine vision inspection systems have replaced human inspectors in defect inspection fields for several decades. However, the inspection results of machine vision are often affected by small changes of illumination. When small changes of illumination appear in image histograms, the influence of illumination can be decreased by transformation of the histogram. In this paper, we propose an enhanced histogram matching algorithm which corrects distorted histograms by variations of illumination. We use the resolution resizing method for an optimal matching of input and reference histograms and reduction of quantization errors from the digitizing process. The proposed algorithm aims not only for improvement of the accuracy of defect detection, but also robustness against variations of illumination in machine vision inspection. The experimental results show that the proposed method maintains uniform inspection error rates under dramatic illumination changes whereas the conventional inspection method reveals inconsistent inspection results in the same illumination conditions.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2021년도 봄 학술논문 발표대회
• /
• pp.275-276
• /
• 2021

In the construction industry, many of the inspection activities have been conducted by experts' eyes. The inspection performance of this kind of method is highly influenced by experience and knowledge of the expert. The experts who have fluent experience may show better inspection performance than the novice. The problem is the deficiency of experts in the near future due to the acceleration of retirement of the aging expert. Eye-tracking technology can be a solution to effectively educate the novice through transferring the knowledge of an expert and to advance the inspection activities using experts' eyes. This study, as an initial step to suggest the solution, (1) figured out the state of the art of eye-tracking technology, (2) reviewed the previous research to improve the inspection in construction using experts' eye, (3) explored the potential of the application area of eye-tracking technology, and (4) established the framework to develop the advanced inspection method in two application area which are construction site safety management and infrastructure performance measurement.

• 한국구조물진단유지관리공학회 논문집
• /
• 제27권5호
• /
• pp.30-39
• /
• 2023

국가의 중요 방재시설인 대형 댐 시설물은 노후화와 홍수, 지진 등의 위험으로 디지털 전환 기술을 적용한 보다 나은 댐 안전점검 및 진단이 필수적이다. 종래의 인력에 의한 육안 안전점검 방식은 인력 접근의 어려움과 고소작업의 위험성, 노하우 중심의 점검에서 오는 데이터의 신뢰성 등의 문제가 있었다. 본 연구에서는 2개 대규모 댐 시설물을 대상으로 드론 photogrammetry에 의한 디지털 데이터 기반 댐 안전점검의 적용성을 검토하고, 지속적 활용을 위한 데이터 관리 방법론을 제시하였다. 댐 높이 42 m 및 99.9 m의 댐들에 대해 수면 및 전자기장 간섭, 심한 고저차에도 불구하고 평면적 더블그리드 및 수동 촬영 방식으로 GSD 2.5 cm/pixel 이내의 양호한 3D 디지털 모델을 생성하였다. 생성된 3D 메쉬 모델, 정사영상, 수치표면모형으로 as-built 조건의 종단 및 횡단 선형을 손쉽게 추출하여 댐의 변형 모니터링에 효과적임을 확인하였다. 댐 여수로 등 콘크리트 시설물에 대한 디지털 3D 모델로부터 균열 및 손상부를 효과적으로 검출하고 시각화하였으며, 이는 고소작업의 위험성 및 접근 제약 시설의 안전점검에 활용가능하다. 또한 댐의 안전점검 시 외관 조사망도를 3D 디지털 모델 상에서 매핑하는 방법과 손상 정보 이력 관리를 위한 관계형 데이터베이스 구조화 방안을 제안하였다. SYG댐 여수로 안전점검에 대한 투입 노동력과 시간을 실측한 결과, 드론 photogrammetry 방법은 기존 인력 육안점검에 비해 48%의 생산성 향상 효과를 확인하였다. 드론 photogrammetry 기반 댐 안전점검 디지털 전환은 업무의 생산성과 데이터 신뢰성 향상에 매우 효과적인 것으로 판단된다.