• 전자공학회논문지SC
• /
• 제49권1호
• /
• pp.8-11
• /
• 2012

자동 결함 검사 시스템 (AVI - Automated Vision Inspection Systems)은 디지털 영상을 통하여 표면의 결함을 자동으로 검출해 주는 시스템이다. 일반적으로 AVI 시스템의 성능은 한도 결함 검출력으로 판별한다. 한도 결함이란 결함 신호가 배경신호와 매우 유사하여 명확히 결함을 검출하기 어렵다. 본 논문에서는 신호대잡음비 (SNR - Signal to Noise Ratio)를 개선할 수 있는 전처리 기법을 제안하였다. 제안된 기법은 인간 시각 시스템 (HVS - Hunman Visual System) 원리를 기반으로 하였으며 이를 RLC (Run Length Code)로 구현하였다. 실험결과 제안된 전처리 기법은 한도 결함 영상에 대해 SNR이 두 배 이상 개선되는 효과를 보였으며 이를 이용하면 AVI 시스템의 검출성능 향상을 기대할 수 있다.

• 전자공학회논문지SC
• /
• 제45권3호
• /
• pp.42-50
• /
• 2008

본 논문은 다양한 제품의 불량 검사를 위한 비전 검사시스템을 개발하였다. 대부분의 기존 검사 시스템은 하나의 제품에 대하여 검사가 가능하도록 설계되었다. 그래서 동일한 검사시스템에서 다른 제품을 검사하기 위해서는 비용과 시간을 들여 시스템을 업데이트하거나 교체를 해야 했다. 본 논문에서는 추가적인 작업이 없어도 적은 비용으로 다양한 제품을 검사할 수 있는 유연한 검사시스템을 제안하였다. 이를 위해 사용하기 편리한 사용자 인터페이스와 특별한 변경 없어도 다양한 제품에 적용 가능한 영상처리 알고리즘을 제안하였다. 제안한 알고리즘은 히스토그램의 형태에 따라 제한된 범위 내에서 임계값을 변경하면서 정상제품 이미지와 불량제품 샘플 이미지간의 상관계수를 구하고 구한 상관계수에서 가장 작은 것을 해당 제품의 검사에 사용할 임계값으로 결정한다. 시스템을 검증하기 위해 핸드폰 케이스 불량 검사에 적용하여 Otsu의 방법과 비교하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.139-142
• /
• 2000

$\mu$BGA(Ball Grid Array) is growing in response to a great demand for smaller and lighter packages for the use in laptop, mobile phones and other evolving products. However it is not easy to find its defect by human visual due to in very small dimension. From this point of view, we are interested its development of a vision based automated inspection algorithm. For this, first a 2D view of $\mu$BGA is described under a special blue illumination. Second, a notation-invariant 2D inspection algorithm is developed. Finally a 3D inspection algorithm is proposed for the case of stereo vision system. As a simulation result, it is shown that 3D defect not easy to find by 2D algorithm can be detected by the proposed inspection algorithm.

• 디지털산업정보학회논문지
• /
• 제7권4호
• /
• pp.81-88
• /
• 2011

Mini Double Gears Frame is critical part of PDP and also produces couple hundred thousand every month. In the process of mass production, product inspection is very important process. Double Gear, one of the part of machine, was inspected by human eyes which caused mistakes and slow progress. To achieve the speed and accuracy the system was compensated by vision system which is inspecting automatically. The focus value is measured based on the fact that high contrast images have much high frequency edge information. High frequency term of the image is extracted using the high-pass filter and the sum of the high frequency term is used as the focus value. We used a Gaussian smoothing filter to reduce the noise and then measures the focus value using the modified Laplacian filter called a Sum modified Laplacian Focus values for the various lens positions are calculated and the position with the maximum focus value is decided as the focused position. The focus values calculated in various lens position showed the Gaussian distribution. We proposed a method to estimate the best focus position using the Gaussian curve fitting. Focus values of the uniform interval lens positions are calculated and the values are used to estimate the Gaussian distribution parameters to find the best focus position.

• 반도체디스플레이기술학회지
• /
• 제12권2호
• /
• pp.57-61
• /
• 2013

This paper presents adaptive neuro-fuzzy inference based defect detection method for various defect types, such as micro-crack, fingerprint and contamination, in heterogeneously textured surface of polycrystalline solar wafers. Polycrystalline solar wafer consists of various crystals so the surface of solar wafer shows heterogeneously textures. Because of this property the visual inspection of defects is very difficult. In the proposed method, we use local binary feature and fuzzy reasoning for defect detection. Experimental results show that our proposed method achieves a detection rate of 80%~100%, a missing rate of 0%~20% and an over detection (overkill) rate of 9%~21%.

• Smart Structures and Systems
• /
• 제14권4호
• /
• pp.719-741
• /
• 2014

Monitoring surface cracks is important to ensure the health of concrete structures. However, traditional visual inspection to monitor the concrete cracks has disadvantages such as subjective inspection nature, associated time and cost, and possible danger to inspectors. To alter the visual inspection, a complete procedure for automated crack assessment based on adaptive digital image processing has been proposed in this study. Crack objects are extracted from the images using the subtraction with median filter and the local binarization using the Niblack's method. To adaptively. determine the optimal window sizes for the median filter and the Niblack's method without distortion of crack object an optimal filter size index (OFSI) is proposed. From the extracted crack objects using the optimal size of window, the crack objects are decomposed to the crack skeletons and edges, and the crack width is calculated using 4-connected normal line according to the orientation of the local skeleton line. For an image, a crack width nephogram is obtained to have an intuitive view of the crack distribution. The proposed procedure is verified from a test on a concrete reaction wall with various types of cracks. From the crack images with different crack widths and patterns, the widths of cracks in the order of submillimeters are calculated with high accuracy.

• Structural Monitoring and Maintenance
• /
• 제2권3호
• /
• pp.283-300
• /
• 2015

Visual condition inspections remain paramount to assessing the current deterioration status of a bridge and assigning remediation or maintenance tasks so as to ensure the ongoing serviceability of the structure. However, in recent years, there has been an increasing backlog of maintenance activities. Existing research reveals that this is attributable to the labour-intensive, subjective and disruptive nature of the current bridge inspection method. Current processes ultimately require lane closures, traffic guidance schemes and inspection equipment. This not only increases the whole-of-life costs of the bridge, but also increases the risk to the travelling public as issues affecting the structural integrity may go unaddressed. As a tool for bridge condition inspections, Unmanned Aerial Vehicles (UAVs) or, drones, offer considerable potential, allowing a bridge to be visually assessed without the need for inspectors to walk across the deck or utilise under-bridge inspection units. With current inspection processes placing additional strain on the existing bridge maintenance resources, the technology has the potential to significantly reduce the overall inspection costs and disruption caused to the travelling public. In addition to this, the use of automated aerial image capture enables engineers to better understand a situation through the 3D spatial context offered by UAV systems. However, the use of UAV for bridge inspection involves a number of critical issues to be resolved, including stability and accuracy of control, and safety to people. SLAM (Simultaneous Localisation and Mapping) is a technique that could be used by a UAV to build a map of the bridge underneath, while simultaneously determining its location on the constructed map. While there are considerable economic and risk-related benefits created through introducing entirely new ways of inspecting bridges and visualising information, there also remain hindrances to the wider deployment of UAVs. This study is to provide a context for use of UAVs for conducting visual bridge inspections, in addition to addressing the obstacles that are required to be overcome in order for the technology to be integrated into current practice.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.13-22
• /
• 2020

Reinforcement steel fixing is a skilled and manually intensive construction trade. Current practice for the quality assessment of reinforcement steel fixing is normally performed by fabricators and has high potential in having errors due to the tedious nature of the work. In order to overcome the current inspection limitation, this study presents an approach that provides visual assistance and inspection enhancement for inspectors to assess the dimensional layout of reinforcement steel fixing. To this end, this study aims to establish an end-to-end framework for rebar layout quality inspection using laser scanning and Augmented Reality (AR). The proposed framework is composed of three parts: (1) the laser-scanned rebar data processing; (2) the rebar inspection procedure integrating with AR; and (3) the checking and fixing the rebar layout through AR visualization. In order to investigate the feasibility of the proposed framework, a case study assessing the rebar layout of a lab-scaled formwork containing two rebar layers is conducted. The results of the case studies demonstrate that the proposed approach using laser scanning and AR has the potential to produce an intuitive and accurate quality assessment for the rebar layout.

• 전자공학회논문지B
• /
• 제33B권11호
• /
• pp.53-61
• /
• 1996

In this paper, efficient techniques for solder joint inspection have been described. Using three layers of ring shaped LED's with different illumination angles, three frames of images are sequentially obtained. From these images the regions of interest (soldered regions) are segmented, and their characteristic features including the average gray level and the percentage of highlights - refereed to as 2D features - are extracted. Based on the backpropagation algorithm of neural networks, each solder joint is classified intor one of the pre-defined types. If the output value is not in the confidence interval, the distribution of tilt angles-referred to as 3D features - is claculated, and the solder joint is classified based on the bayes classfier. The second classifier requires more computation while providing more information and better performance. The proposed inspection system has been implemented and tested with various types of solder joints in SMDs. The experimental results have verified the validity of this scheme in terms of speed and recognition rate.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.389-390
• /
• 2006

The goal of this paper is automation of a remocon inspection process using machine vision system. This system prevents error that is occurred by physical and spirit condition of human. Also this system has been developed to raise the reliability of remocon inspection. This system has been developed only using PC, CCD Camera and Visual C++ for universal workplaces. The performance of this system is an accuracy improvement of $2{\sim}3[%]$ and a processing time reduction of about 100[ms] against existing pattern matching method.