• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.7-13
• /
• 2021

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.

• Journal of Sensor Science and Technology
• /
• v.30 no.2
• /
• pp.76-81
• /
• 2021

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.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.7
• /
• pp.741-749
• /
• 2014

This paper proposes a machine vision module for PLCs (Programmable Logic Controllers). PLC is the industrial controller most widely used in factory automation system. However most of the machine vision systems are based on PC (Personal Computer). The machine vision system embedded in PLC is required to reduce the cost and improve the convenience of implementation. In this paper, we newly propose a machine vision module based on PLC. The image processing libraries are implemented and integrated with the PLC programming tool. In order to interface the libraries with ladder programming, the ladder instruction set was also designed for each vision library. By use of the developed system, PLC users can implement vision systems easily by ladder programming. The developed system was applied to sample inspection system to verify the performance. The experimental results show that the proposed system can reduce the cost of installing as well as increase the ease-of-implementation.

• Journal of Biosystems Engineering
• /
• v.22 no.2
• /
• pp.210-216
• /
• 1997

A study to select ground colors of Fuji apple for maturity index which are needed to standardize grading of the apples is presented. Two extreme colors of immature and fully mature Fuji and Zonagold apples produced in Korea were determined. Various ground colors of Fuji apple between the two extreme colors were collected and classified by human vision and colors of Fuji apple for maturity index were selected from the classification. Coordinates of the selected colors in xy chromaticity diagram were determined by spectrophotometers to define them in a standard coordinate system. Coordinates of the colors in r-g chromaticity diagram using a color machine vision system were also determined to use the colors in apple grading by the machine vision system. Grading Fuji apples using the machine vision system was performed and result of the grading was compared with Ending results of human vision and colorimeter. The comparison was performed with the same Fuji apple samples and showed 65% md 75% of same grades, respectively, as the grades determined by the machine vision system. Differences of fading performance between the compared three grading methods were explained as mainly because of the differences of observation area of the grading methods.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.153-154
• /
• 2006

Development of sorting machine for photo diode and its control system is addressed. The sorting machine for optical communication device requires high positional precision because the alignment is one of the most important point in the sorting process. This sorting method describes how to detect the target chip's angle and position from the wafer. The machine vision system is used for the feedback control. This sorting machine is implemented by motion controller, machine vision and various solenoid valve and is interfaced with RS-232c, GPIB and PCI communication. This system gets the position accuracy within $1{\mu}m$ with our experiments.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.5
• /
• pp.177-185
• /
• 2001

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.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.20 no.1
• /
• pp.53-59
• /
• 2011

End milling is available for machining the various shape of products and has been widely applied in many manufacturing industries. The quality of products depends on a machine tool performance and machining conditions. Recognition characteristics of the cutting condition is becoming a critical requirement for improving the utilization and flexibility of present-day CNC machine tools. The measurement of tool wear would be performed by coordinate-measuring machine(CMM). However, the usage of CMM requires much time and cost. In order to overcome the difficulties, on-line measurement(OLM) system was applied for a tool wear measurement. This study shows a reliable technique for the reduction of machining error components by developing a system using a CCD camera and machine vision to be able to precisely measure the size of tool wear in flat end milling for CNC machining. The CCD camera and machine vision attached to a CNC machine can determine tool wear quickly and easily.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.6 s.249
• /
• pp.713-721
• /
• 2006

Micro-drill wear deteriorates accuracy and productivity of the micro components. In order to improve productivity and qualify of micro components, it is required to investigate micro-drill wear exactly. In this study, a machine vision system is proposed to measure the wear of micro-drills using a precision servo stage. Calibration experiments are conducted to compensate for the machine vision system. In this paper, worn volume, area and length are defined as wear amounts. Micro-drill wear is reconstructed as the 3D topography and the quantized wear amount by using the shape from focus (SFF) method and wear parameters. Experiments have been conducted with HSS twist micro-drills and SM45C carbon steel workpieces. Validity of the proposed machine vision system is confirmed through experiments.

• Journal of information and communication convergence engineering
• /
• v.20 no.4
• /
• pp.317-325
• /
• 2022

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.

• Journal of Biosystems Engineering
• /
• v.28 no.3
• /
• pp.231-238
• /
• 2003

Rose and chrysanthemum are the most popular flowers in Korean floriculture. Sorting flowers is a labor intensive operation in cultivation of the cut flowers and needed to be mechanized. Machine vision is one of the promising solutions for this purpose. This study was carried out to develop hardware and software of a cut flower sorting system using machine vision and to test its performance. Results of this study were summarized as following; 1. Length of the cut flower measured by the machine vision system showed a good correlation with actual length of the flower at a level of the coefficients of determination (R$^2$) of 0.9948 and 0.9993 for rose and chrysanthemum respectively and average measurement errors of the system were about 2% and 1% of the shortest length of the sample flowers. The experimental result showed that the machine vision system could be used successfully to measure length of the cut flowers. 2. Stem diameter of the cut flowers measured by the machine vision system showed a correlation with actual diameter at the coefficients of determination (R$^2$) of 0.8429 and 0.9380 for rose and chrysanthemum respectively and average measurement errors of the system were about 15% and 7.5% of the shortest diameter of the sample flowers which could be a serious source of error in grading operation. It was recommended that the error rate should be considered to set up grading conditions of each class of the cut flowers. 3. Bud maturity of 20 flowers each judged using the machine vision system showed a coincidence with the judgement by inspectors at ranges of 80%∼85% and 85%∼90% for rose and chrysanthemum respectively. Performance of the machine vision system to judge bud maturity could be improved through setting up more precise criteria to judge the maturity with more samples of the flowers. 4. Quality of flower judged by stem curvature using the machine vision system showed a coincidence with the judgement by inspectors at 90% for good and 85% for bad flowers of both rose and chrysanthemum. The levels of coincidence was considered as that the machine vision system used was an acceptable system to judge the quality of flower by stem curvature.