• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.474-478
• /
• 2024

In this paper, we proposes a deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers. The proposed deep learning network is specifically designed for pharmaceutical containers by using data produced in real manufacturing environments, leading to more accurate quality inspection. Additionally, the use of an inline-capable deep learning network allows for an increase in inspection speed. The development of the deep learning network for quality inspection in the multi-camera inline inspection system consists of three steps. First, a dataset of approximately 10,000 images is constructed from the production site using one line camera for foreign substance inspection and three area cameras for dimensional inspection. Second, the pharmaceutical container data is preprocessed by designating regions of interest (ROI) in areas where defects are likely to occur, tailored for foreign substance and dimensional inspections. Third, the preprocessed data is used to train the deep learning network. The network improves inference speed by reducing the number of channels and eliminating the use of linear layers, while accuracy is enhanced by applying PReLU and residual learning. This results in the creation of four deep learning modules tailored to the dataset built from the four cameras. The performance of the proposed deep learning network for quality inspection in the multi-camera inline inspection system for pharmaceutical containers was evaluated through experiments conducted by a certified testing agency. The results show that the deep learning modules achieved a classification accuracy of 99.4%, exceeding the world-class level of 95%, and an average classification speed of 0.947 seconds, which is superior to the world-class level of 1 second. Therefore, the effectiveness of the proposed deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers has been demonstrated.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.469-473
• /
• 2024

In this paper proposes a study on the development of a multi-camera inline inspection system using machine vision for quality inspection of pharmaceutical containers. The proposed technique captures the pharmaceutical containers from multiple angles using several cameras, allowing for more accurate quality assessment. Based on the captured data, the system inspects the dimensions and defects of the containers and, upon detecting defects, notifies the user and automatically removes the defective containers, thereby enhancing inspection efficiency. The development of the multi-camera inline inspection system using machine vision is divided into four stages. First, the design and production of a control unit that fixes or rotates the containers via suction. Second, the design and production of the main system body that moves, captures, and ejects defective products. Third, the design and development of control logic for the embedded board that controls the entire system. Finally, the design and development of a user interface (GUI) that detects defects in the pharmaceutical containers using image processing of the captured images. The system's performance was evaluated through experiments conducted by a certified testing agency. The results showed that the dimensional measurement error range of the pharmaceutical containers was between -0.30 to 0.28 mm (outer diameter) and -0.11 to 0.57 mm (overall length), which is superior to the global standard of 1 mm. The system's operational stability was measured at 100%, demonstrating its reliability. Therefore, the efficacy of the proposed multi-camera inline inspection system using machine vision for the quality inspection of pharmaceutical containers has been validated.

• 한국신재생에너지학회:학술대회논문집
• /
• 2007.11a
• /
• pp.231-231
• /
• 2007

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.5
• /
• pp.2113-2120
• /
• 2013

In this study, an efficient machine vision based inspection system is developed for the in-line measurement of phosphor resin dispensing shapes on LED chip package. Since the phosphor resin (target material) has semitransparent characteristics, illuminated light beam is reflected from the bottom of the chip as well as from the surface. Since such phenomenon can deteriorate inspection reliability, a white LED and a 635nm laser slit beams are experimentally tested to decide suitable illumination optics. Also, specular and diffuse reflection methods are tested to decide suitable optical triangulation. As a result, it can be known that the combination of a white slit beam source and specular reflection method show the best inspection results. The Catmull-Rom spline interpolation is applied to the obtained data to form smoother surface. From the results, it can be conclude that the developed system can be sucessfully applied to the in-line inspection of LED chip packaging process.

• Journal of the Korean Applied Science and Technology
• /
• v.36 no.2
• /
• pp.541-550
• /
• 2019

This study is aimed to find out the effect of PAPS-D on physical fitness of developmental disabled students who participated of Inline skate program. The subject of this study was 10 middle and high school students diagnosed as developmental disability. The subject attended a total of 32 classes twice a week for 16 weeks and the class was 1 hour each time. Improvement of physical fitness was assessed based on PAPS-D program developed by the Department of Education science in 2016 except for obesity measurement; cardio pulmonary function (walking in 6 minutes), flexibility (seated forward bend, clasped hand behind the back), muscle function (sit-up) and agility (standing long jump). To find out the interaction between control group and experimental group, two-way repeated measure ANOVA was used. As a result, there was a statistically significant relation in cardio pulmonary function and agility but not in flexibility and muscle function. 3 variables (cardio pulmonary function, flexibility and muscle function) among 4 variables showed positive effect of Inline skate program on physical fitness while one variable which was agility showed decreased result in post-test. Based on the results of three variables that were found to have improved in the pre post-examination, the result of this study indicates positive effect of Inline skating program on physical fitness of developmentally disabled students.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.694-699
• /
• 2012

In this paper, semiconductor package inspection results using white light interferometer with large F.O.V., in order to apply semiconductor product inspection process, are shown. Experimental 3D data repeatability test results for the same special bumps of each substrate are shown. Experimental 3D data repeatability test results for all the bumps in each substrate are also shown. Semiconductor package inspection using white light interferometer with large F.O.V. is very important for the fast 3D data inspection in semiconductor product inspection process. This paper is surely helpful for the development of in-line type fast 3D data inspection machine.

• The Optical Journal
• /
• s.177
• /
• pp.46-53
• /
• 2020

• Journal of Korea Multimedia Society
• /
• v.13 no.2
• /
• pp.196-204
• /
• 2010

In this paper, we develope a defect inspection method for each buttons of keypad of cellular phones before they are assembled. The proposed algorithm consists of the similar color checking and its classification, font error detection, and scratch detection based on the segmentation of keypad area and font, translation and rotation processing sequentially. Especially, the proposed segmentation method approximate the pad region as B-spline function to deal with illumination change due to the shape of key button with the slant and curved surface followed by simple thresholding. And also, the rotational information is obtained by using eigen value and eigen vector very fast and effectively. The experimental results show that the performance of the proposed algorithm is good when it is applied to in-line process.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.4
• /
• pp.286-291
• /
• 2013

In this paper, in-line type flip chip bump 3D inspection equipment, using white light interferometer with large F.O.V., which is aimed to be used in flip chip bump test process is developed. Results of flip chip bump height measurement in many substrates and repeatability test results for the bumps in fixed location of each substrate are shown. Test results from test bench and those from developed flip chip bump 3D inspection equipment are compared and as a result repeatability is improved by reducing the impact of system vibration. A valuation basis for the testing quality of flip chip bump 3D inspection equipment is proposed.

• Journal of Korean Society for Quality Management
• /
• v.23 no.3
• /
• pp.33-44
• /
• 1995

This paper presents an automated visual inspection system for the electronic parts manufacturing process. In this system, a statistical process control (SPC) method is integrated into the automated inspection method on a real time base. It shows how the collected data can be analyzed with the SPC to provide process information. Also presented are studies of subpixel image processing technology to improve the accuracy of parts measurements, and the cumulative-sum (CUSUM) control chart for fraction defectives. An application of the developed system to connector manufacturing process as a part of computer integrated manufacturing (CIM) is presented.