• Journal of Digital Convergence
• /
• v.10 no.10
• /
• pp.301-306
• /
• 2012

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.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.4
• /
• pp.1683-1691
• /
• 2013

Concrete surface grinding is frequently used for flatness of concrete surface, concrete pavement rehabilitation, and adhesiveness in pavement construction. The procedure is, however, labor intensive and has a hazardous work condition. Also, the productivity and the quality of concrete surface grinding highly depend on the skills of worker. Thus, the development of remote controlled concrete surface grinding equipment is necessary to prevent the environmental pollution and to protect the workers from hazardous work condition. However, it is difficult to evaluate the grinded surface objectively in a remote controlled system. Also, The machine vision system developed in this study takes the images of grinded surface with the network camera for image processing. Then, by representing the quality test results to the integrated program of the remote control station, the quality control system is constructed. The machine vision algorithm means the image processing algorithm of grinded concrete surface and this paper presents the objective quality control standard of grinded concrete surface through the application of the suggested algorithm.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.4
• /
• pp.58-63
• /
• 2009

The appearance inspection of various electronic products and parts was executed by the eyesight of human. The appearance inspection is applied to the most electronic component of LCD Panel, flexible PCB and remote control. If the appearance of electronic products of small and minute size is inspected by the eyesight of human, we can't expect the stable inspection result because inspection result is changed by condition of physical and spirit of the checker. Therefore currently machine vision systems are used to many appearance inspection fields instead of inspection by human. The many problems of inspection by the checker are not occurred in machine vision circumstance. However, the inspection by automatic machine vision system is mainly influenced by illumination of workplace. In this paper, we propose a histogram transform method for improving accuracy of machine visual inspection.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.4 no.2
• /
• pp.91-97
• /
• 2012

The automated visual inspection system (machine vision system) for quality assurance is an important factory automation equipment in the manufacturing industries, such as display, semiconductor, etc. The world market of the machine vision components is expected 18 billon dollars in 2015. Therefore, there is a lot of demand for the machine vision engineers. However, there are no technical training courses for machine vision technologies in vocational schools, colleges and universities. In this paper, we propose a technical training program for the machine vision technology. The total time of training is 30 to 60 hours and the training program can operate flexibly by student's major, a priori knowledge and education level.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.70-75
• /
• 2016

Nowadays, there are many research for recognizing face of people using the machine vision. the machine vision is classification and analysis technology using machine that has sight such as human eyes. In this paper, we propose algorithm for classifying human face using this machine vision system. This algorithm consist of Convolutional Neural Network and cascade face detector. And using this algorithm, we classified the face of subjects. For training the face classification algorithm, 2,000, 3,000, and 4,000 images of each subject are used. Training iteration of Convolutional Neural Network had 10 and 20. Then we classified the images. In this paper, about 6,000 images was classified for effectiveness. And we implement the system that can classify the face of subjects in realtime using USB camera.

• Broadcasting and Media Magazine
• /
• v.28 no.1
• /
• pp.38-52
• /
• 2023

오늘날 인터넷 트래픽의 80% 이상은 이미지와 비디오와 같은 영상 정보가 차지하고 있으며, 딥러닝 기술의 발전과 더불어 영상을 사람이 아닌 머신이 처리하는 경우가 점점 늘어가고 있다. 사람의 시각적 특성과 머신이 처리하는 특징이 다를 수 있다는 점을 고려하여 MPEG을 비롯한 표준화 단체에서 딥러닝 네트워크를 포함한 기계(머신)를 위한 비디오 부호화에 대하여 표준화를 진행 중에 있다. 본 기고에서는 MPEG에서 진행되고 있는 머신 비전을 위한 영상 부호화 표준화 동향에 대해 정리한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.657-660
• /
• 2002

현재 Embedded system 에서 많은 기업체들이 리눅스를 채용하고 있고, 이러한 임베디드 리눅스는 실시간 운영체제가 필요한 로봇제어기에서부터 PDA, set-top box등 여러 분야에 걸쳐 응용되고 있다. 본 논문에서는 StrongARM SA-1110 CPU을 이용하여 만들어진 임베디드 시스템에 리눅스를 사용하여 독립형 비전모듈을 개발한 내용을 기술한다. 또한, WinCE 를 사용하여 개발된 비전모듈과의 성능을 비교하여 리눅스를 이용한 독립형 비전모듈을 평가하고, 머신비전 분야에서의 리눅스 응용 가능성을 제시하였다.

• Proceedings of the KAIS Fall Conference
• /
• 2007.05a
• /
• pp.32-34
• /
• 2007

본 논문에서는 자동차 핵심부품 중 하나인 알터네이터 수풀의 육안검사를 대체하기 위한 머신비전시스템을 개발하는 목적이 있다. 플라스틱 사출물의 경우 일반적으로 미성형, 찍힘, 뜯김, 크랙 등의 불량 유형이 발생하는 데, 이를 전수검사하기 위한 머신비전 시스템의 설계와 검사 알고리즘을 개발하고자 한다. 개발된 시스템은 산업현장에 적용하여 절대적판정의 안정성을 도모하고, 생산성 향상 및 부품의 표준화를 확립하는 데 기여할 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.37-38
• /
• 2023

본 논문에서는 딥러닝을 기반으로 하는 키포인트 인식 모델을 산업용 품질검사 머신비전에 응용하는 방법을 제안한다. 전이학습 방법을 이용하여 딥러닝 모델의 인식률을 높이는 방법을 제시하였고, 전이시킨 특성 추출 모델에 대해 추가로 데이터 세트에 대한 학습을 진행하는 것이 특성추출 모델의 초기 ImageNet 가중치를 동결시켜 학습하는 것보다 학습 속도나 정확도가 높다는 것을 보여준다. 실험을 통해 딥러닝을 응용하는 산업용 품질 검사 공정에는 특성추출 모델의 추가 학습이 중요하다는 점을 확인할 수 있었다.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.983-986
• /
• 2007

Concrete surface grinding is required for flatness and adhesiveness of concrete surface. The procedure is, however, labor intensive and has a hazardous work condition. Also, the productivity and the quality of concrete surface grinding depend on the levels of worker. Thus, the development of remote controlled concrete surface grinding equipment is necessary to prevent the environmental pollution and to protect the workers from hazardous work condition. However, it is difficult to evaluate the grinded surface objectively in a remote controlled system. The machine vision system developed in this study takes the images of grinded surface with the network camera for image processing. Then, by representing the quality test results to the graphic MMI program of the remote control station, the quality control system is constructed. The machine vision algorithm means the image processing algorithm of grinded concrete surface and this paper presents the objective quality control standard of grinded concrete surface through the application of the suggested algorithm.