Earticle

본 논문은 머신비전시스템에서 정확한 이미지 획득을 위한 방법을 제안한다. 각종 렌즈에서 요구되는 가장 중요한 기능으로는 실물과 동일한 고품질의 결상을 구현하는 광학적 역할이다. 그러나 머신비전시스템의 입력부에서는 렌즈의 수차로 인하여 왜곡현상이 발생한다. 이러한 문제를 해결하기 위해 실세계 좌표계와 영상 좌표계 간의 변환 관계를 정의해주는 매핑 기능으로, 행렬연산을 통하여 두 좌표간의 거리를 계산하여 정확한 위치를 지정하게 된다. 레이저 정밀 가공작업에서도 Galvanometer를 사용하면 비구면 초점 렌즈에 의하여 발생되고 있는 렌즈 수차를 보정하여야 가공 오차를 개선 할 수 있다. 비구면 렌즈의 수차는 2차원 곡선의 형태를 가지고 있으나, 기존의 렌즈 보정 방법인 선형방법은 매우 많은 점들을 검사하여 보정시간이 많이 소요되는 문제점이 있었다. 가공장비에서 렌즈의 수차로 인하여 발생하는 가공오차를 감소시키기 위하여 Bilinear interpolation 기법을 적용하는 방법을 제안하였다. 제안한 방법은 기존 선형방법과 비교하여 위치 오차의 평균값과 표준편차가 향상되었음 실험을 통하여 입증하였으며 실제 레이저 응용업무에 적용하고 있다.

We propose a method for accurate image acquisition in a machine vision system in the present study. The most important feature is required by the various lenses to implement real and of the same high quality image-forming optical role. The input of the machine vision system, however, is generated due to the aberration of the lens distortion. Transformation defines the relationship between the real-world coordinate system and the image coordinate system to solve these problems, a mapping function that matrix operations by calculating the distance between two coordinates to specify the exact location. Tolerance Focus Lens caused by the lens aberration correction processing to Galvanometer laser precision machining operations can be improved. Aberration of the aspheric lens has a two-dimensional shape of the curve, but the existing lens correction to linear time-consuming calibration methods by examining a large number of points the problem. How to apply the Bilinear interpolation is proposed in order to reduce the machining error that occurs due to the aberration of the lens processing equipment.

In this study, we propose a technological system designed to provide machine vision-based automatic inspection and autonomous operation services for an entire process related to product inspection in wire harness manufacturing. The smart factory paradigm is a valuable and necessary goal, small companies may encounter steep barriers to entry. Therefore, the best approach is to develop towards this approach gradually in stages starting with the relatively simple improvement to manufacturing processes, such as replacing manual quality assurance stages with machine vision-based inspection. In this study, we consider design issues of a system based on the proposed technology and describe an experimental implementation. In addition, we evaluated the implementation of the proposed technology. The test results show that the adoption of the proposed machine vision-based automatic inspection and operation service system for multi-wire harness production may be considered justified, and the effectiveness of the proposed technology was verified.

This study proposes a novel video traffic flow detection method based on machine vision technology. The three-frame difference method, which is one kind of a motion evaluation method, is used to establish initial background image, and then a statistical scoring strategy is chosen to update background image in real time. Finally, the background difference method is used for detecting the moving objects. Meanwhile, a simple but effective shadow elimination method is introduced to improve the accuracy of the detection for moving objects. Furthermore, the study also proposes a vehicle matching and tracking strategy by combining characteristics, such as vehicle's location information, color information and fractal dimension information. Experimental results show that this detection method could quickly and effectively detect various traffic flow parameters, laying a solid foundation for enhancing the degree of automation for traffic management.

Background/Objectives: The Philippine government through the Department of Science and Technology (DOST) helps the micro, small, and medium enterprises (MSMEs) to support and sustain growth and address their needs on availing cost-effective solutions. Methods/Statistical analysis: Most of the MSMEs which apply clear bottles for their products use manual inspection. These are prone to human error that leads to poor product qualities and rejects. Findings: To address these problems, this study presents a cost-effective solution by a rule-based machine vision system for clear empty glass base inspection. A method on proper setup for the inspection is presented and validated through an in-line loop on a wedge conveyor machine prototype. A minimal setup time was achieved by experimenting different lighting techniques. Improvements/Applications: The use of back light illumination is suggested for good image processing quality with minimal cost. The implementation of a rule-based inspection in this setup results to a high speed of 9000-18000 bottles per hour (bph) with consistent repeatability and superior accuracy.

Background: We developed a machine vision technology program that tracks patients’ realtime breathing and automatically analyzes their breathing patterns. Materials and Methods: To evaluate its potential for clinical application, the image tracking performance and accuracy of the program were analyzed using a respiratory motion phantom. Changes in the stability and regularity of breathing were observed in healthy adult volunteers according to whether the breathing pattern mirrored the breathing guidance. Results and Discussion: Displacement within a few millimeters was observed in real-time with a clear resolution, and the image tracking ability was excellent. This result was consistent even in the sections where breathing patterns changed rapidly. In addition, the respiratory gating method that reflected the individual breathing patterns improved breathing stability and regularity in all volunteers. Conclusion: The findings of this study suggest that this technology can be used to set the appropriate window and the range of internal target volume by reflecting the patient’s breathing pattern during radiotherapy planning. However, further studies in clinical populations are required to validate this technology.

This paper describes a machine-vision-based prototype system for automatically feeding engine-mount parts to a swaging machine which assembles engine mounts. The system developed consists of a robot, a feeding device with two cylinders and two photo sensors, and a machine vision system. The machine vision system recognizes the type of different parts being fed from the feeding device and estimates the angular difference between the inner-hole center of the part and the point predetermined for assembling. The robot then picks up each part and rotated it through the estimated angle such that the parts are well assembled together as specified. An algorithm has been developed to recognize different part types and estimate the angular difference. The test results obtained for a set of real specimens indicate that the algorithm performs well enough to be applied to prototype system.

A novel method of dimensional measurement using machine vision, which is called Landmark Tracking System, has been developed. Its advantages come form tracking only the bright, standard shaped "landmarks" which are made from retroreflective sheets. In the design of the LTS, it is essential to know the relationship between optical parameters and their influence on system performance. Such optical parameters include the brightness of landmark image, the illumination system design, and the choice of imaging optics. And the performance of retroreflective material also plays important role in the LTS performances. Influences of such optical parameters on LTS's dimensional measurement characteristics are investigated, with respect to the retroreflective material, the imaging optics, and the illumination system. Measuremtn errors due to parameter variations are also analyzed. Experiments are performed with a LTS prototype. Retroreflective characteristics are verified, and the LTS's measurement performances are measured in the form of repeatability and accuracy. Experimental results shgow that the LTS has repeatability better than 1/30,000 of a field of view(30 degrees), and accuracy better tha 1/3,000 of a field fo view.d fo view.

The integrity and accuracy of the drilling hole are decided by positional error, diameter error, the roundness, the straightness, the cylindericity, size of the burr, the surface roundness and others. Among these parameters, positional error and diameter error have the most important parameters. The diameter error has been widely studied, but there has been little research done about the positional error due to the difficulty of measuring it. The measurement of hole location and diameter would be performed by CMM(Coordinate Measurement Machine). However, the usage of CMM requires much time and cost. In order to overcome the difficulties, we have developed a hole location and diameter error measuring device using machine vision. The developed measurement device attached to a CNC machine can determine hole quality quickly and easily.

본 논문은 딥러닝을 기반으로하여 SMT 공정 중 스크린 프린터를 통과한 PCB를 확인하여 솔더크림이 지정 된 위치에 일정한 높이로 도포되지 않은 경우 불량 PCB로 간주하고 해당 PCB의 불량 위치를 경계상자로 설정하 도록 하는 딥러닝 적용 불량검출 AI엔진 시스템 설계 및 개발에 관한 연구이다. 솔더크림 도포 불량 유형은 자주 발생되는 7가지로 구성하였으며 실증 업체로부터 불량 PCB를 수집하여 촬영하고 데이터셋을 준비하였다. 학습에 사용된 데이터셋은 Train, Validation, Test의 그룹으로 나누어 RT-DETR 모델을 기반으로 훈련시켰다. 연구 결 과 목표로 삼은 7개 유형의 결함이 성공적으로 탐지됨을 확인할 수 있었다. 이후 추가적인 현장 실증 및 고도화를 통하여 SMT공정 중 스크린 프린팅 결과물을 대상으로 실시간 불량을 식별해 내는 AI머신비전 시스템으로써 역할 을 크게 할 것으로 기대된다.

This paper is about the design and development of a defect detection AI engine system based on deep learning that checks a PCB that passed through a screen printer during the SMT process, and if the solder cream is not applied to a specified location and at a certain height, it is considered a defective PCB and sets the defective location of the PCB as a bounding box. The types of solder cream application defects consisted of seven frequently occurring types, and defective PCBs were collected from a verification company, photographed, and a dataset was prepared. The dataset used for learning was divided into groups of Train, Validation, and Test and trained based on the RT-DETR model. As a result of the study, it was confirmed that the seven types of defects targeted were successfully detected. In the future, through field verification and advancement, it is expected to play a significant role as an AI machine vision system that identifies defects in real time for screen printing results during the SMT process.

This paper is about the development of Automatic FPC(flexible printed circuit) punching instrument for the improvement of working condition and cost saving. FPC is used to detect the contact position of keyboard and button like a cellular phone. Depending on the quality of the printed ink and position of reference punching point to the FPC, the resistance and current are varied to the malfunctioning values. The size of reference punching point is 2mm and the above. Because the punching operation is done manually, The punching accuracy is varied with operator's condition. Recently, The punching accuracy has deteriorated severely to the 2mm punching reference hall so that assembly of the K/B has hardly done. To improve this manual punching operation to the FPC, automatic FPC punching system is introduced. Precise mechanical parts like a 5-step stepping motor and ball screw mechanism are designed and tested and low cost PC camera is used fur the sake of cost down instead of using high quality vision systems for the factory automation. Test algorithms and programs showed good results to the designed automatic punching system and led to the increasement of productivity and huge cost down to law material like FPC by avoiding bad quality.

The objective of this research is in the development of a flexible 3-dimensional inspection system for the sculptured surface by integrating the Coordinate Measuring Machine (CMM), CAD database, and vision system. To achieve the proposed flexible inspection system, two research categories are discussed in the study: new inspection planning method includes a new measuring point selection method and various new probe path generation methods. The object recognition and localization process for the unknown surface can be easily carried out by introducing a new concept called "Z-Layer". The experimental results indicate that the developed flexible inspection system, with the proposed algorithm, can be inplemented in real situation.situation.

Machine vision is a technology that helps the computer as if a person recognizes and determines things. In recent years, as advanced technologies such as optical systems, artificial intelligence and big data advanced in conventional machine vision system became more accurate quality inspection and it increases the manufacturing efficiency. In machine vision systems using deep learning, the image quality of the input image is very important. However, most images obtained in the industrial field for quality inspection typically contain noise. This noise is a major factor in the performance of the machine vision system. Therefore, in order to improve the performance of the machine vision system, it is necessary to eliminate the noise of the image. There are lots of research being done to remove noise from the image. In this paper, we propose an autoencoder based machine vision system to eliminate noise in the image. Through experiment proposed model showed better performance compared to the basic autoencoder model in denoising and image reconstruction capability for MNIST and fashion MNIST data sets.

The sorter working at high speed in semiconductor production process has been a main reason for productivity failure, causing equipment failure and process halt as socket full or full status of the semiconductor package is not monitor in loading and unloading work of the semiconductor package of test socket board. Furthermore, it is necessary to promptly control vacuum to load and unload semiconductor package at high speed, but delicate on/off control error and limitation of engineer's bare eye checking are not free form error to package sorting. Therefore, the present study developed sorter process-focused image (video) processing algorithm and hardware-based MVMS to apply to production lines.

컴퓨터 비전은 카메라를 이용하여 측정대상의 영상을 획득하고, 추출하고자 하는 특징 값, 벡터, 영역 등을 알 고리즘과 라이브러리 함수를 응용하여 검출한다. 검출된 데이터는 사용하는 목적에 따라 다양한 형태로 계산되고 분 석한다. 컴퓨터 비전은 다양한 곳에 활용되고 있으며, 특히 자동차의 부품을 자동으로 인식하거나 품질을 측정하는 분야에 많이 활용된다. 컴퓨터 비전을 산업분야에서 머신비전이라는 용어로 활용되고 있으며, 인공지능과 연결되어 제품의 품질을 판정하거나 결과를 예측하기도 한다. 본 연구에서는 자동차 부품의 품질을 판정하기 위한 비전시스템 을 구축하고, 생산된 데이터에 5개의 머신러닝 분류 모델을 적용하여 그 결과를 비교하였다.

In computer vision, an image of a measurement target is acquired using a camera. And feature values, vectors, and regions are detected by applying algorithms and library functions. The detected data is calculated and analyzed in various forms depending on the purpose of use. Computer vision is being used in various places, especially in the field of automatically recognizing automobile parts or measuring the quality. Computer vision is being used as the term machine vision in the industrial field, and it is connected with artificial intelligence to judge product quality or predict results. In this study, a vision system for judging the quality of automobile parts was built, and the results were compared by applying five machine learning classification models to the produced data.

In this study, we propose a machine vision system with a high object recognition rate. By utilizing a multiple-exposure image sensing technique, the proposed deep learning-based machine vision system can cover a wide light intensity range without further learning processes on the various light intensity range. If the proposed machine vision system fails to recognize object features, the system operates in a multiple-exposure sensing mode and detects the target object that is blocked in the near dark or bright region. Furthermore, short- and long-exposure images from the multiple-exposure sensing mode are synthesized to obtain accurate object feature information. That results in the generation of a wide dynamic range of image information. Even with the object recognition resources for the deep learning process with a light intensity range of only 23 dB, the prototype machine vision system with the multiple-exposure imaging method demonstrated an object recognition performance with a light intensity range of up to 96 dB.

In the present research work, an automated machine vision system and a new algorithm to interpret the inspection data has been developed. In the past, the control of tolerance of front-chassis-module was done manually. In the present work a machine vision system and required algorithm was developed to carryout dimensional evaluation automatically. The present system is used to verify whether the automobile front-chassis-module is within the tolerance limit or not. The directional ability parameters related with front-chassis-module such as camber, caster, toe and king-pin angle are also determined using the present algorithm. The above mentioned parameters are evaluated by the pose of interlinks in the assembly of an automobile front-chassis-module. The location of ball-joint center is important factor to determine these parameters. A method to determine the location of ball-joint center using geometric features is also suggested in this paper. In the present work a 3-D best fitting method is used for determining the relationship between nominal design coordinate system and the corresponding feature coordinate system.