• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.1742-1747
• /
• 1991

Since inspection, ID-code recognition, and pattern match processes requiring vision depend upon the high-grade human recognition capability, these processes have conventionally caused a bottle-neck in automatizing sewing system. However, the authors have recently developed the technology of inspecting the surface defects of textiles and recognizing ID-code by fully utilizing the image processing technology. In the ID-code recognition technology, the most difficult data given on patterns can be read as a result of developing the image processing technology and eliminating noises by using a special (fluorescent) ink. The inspection and pattern match technology was verified to be able to put into practical use through evaluation experiments in an experimental plant.

• 한국정보처리학회논문지
• /
• 제7권6호
• /
• pp.1818-1826
• /
• 2000

This research is one the design and implementation of XSL document authoring system based on the XSL pattern to transform XML document. This system is developed not according to the rule of conventional CSS methods but according to the rule of XSL syntax for document processing language of SML structure. The XSL authoring system supports Korean character documents and is available of various kinds of pattern generations so that it is useful for generation of XSL document. This system is implemented for the environment of Window NT2000 in compatible IBM PC an develops by Visual J++6.0.

• Journal of the Optical Society of Korea
• /
• 제15권3호
• /
• pp.264-271
• /
• 2011

In this paper we examine and compare the computational speeds of three-dimensional (3D) object recognition by use of digital holography based on central unit processing (CPU) and graphic processing unit (GPU) computing. The holographic fringe pattern of a 3D object is obtained using an in-line interferometry setup. The Fourier matched filters are applied to the complex image reconstructed from the holographic fringe pattern using a GPU chip for real-time 3D object recognition. It is shown that the computational speed of the 3D object recognition using GPU computing is significantly faster than that of the CPU computing. To the best of our knowledge, this is the first report on comparisons of the calculation time of the 3D object recognition based on the digital holography with CPU vs GPU computing.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 전문대학교육위원
• /
• pp.62-67
• /
• 2004

In this paper, we present the new method for joint aspect inspecting system. We use the image processing and laser maker for light source. We can find the matrial joint status through processing the line pattern which is made by laser maker. To get the line pattern, in first, we had done the preprocss of threshold. If the shape of line had over two segments, then the joint status is abnormal. We show our system efficency by experiment on tire facility.

• 한국의류학회지
• /
• 제20권2호
• /
• pp.311-322
• /
• 1996

To accomodate workers with efficient mobility, coveralls were redesigned, construted and evaluated. In this study, especially, image processing techniques were applied to the evaluation stage, to quantify thE ease of body movement. For the initial observation stage, car-center workers were interviewed and their movements were videotaped. By analyzing the videotape, the area of stress and strains on the work clothes were marked on the figure chert and considered for the pattern making. 4DM cut pattern were applied to the upper part of the work clothes and other alternations were made throughout the problem area. Honey comb slashes were made on the problem area of the original and newly designed coveralls. Open areas of honey comb slashes due to body movement between the original and newly designed coveralls were analyzed by image processing techniques. Other objective and subjective evaluation of newly designed coveralls was compared with the original one. Overall evaluation of functionally designed coveralls was appered to be positive and the image processing techiques were useful methology to quantify the amount of stress in this study.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2001년도 추계학술대회 논문집
• /
• pp.270-273
• /
• 2001

Electrical tree is studied widely by manufacture state of insulating material fare and blazing fire diagnosis system of use in phenomenon of part discharge that happen for main cause of dielectric breakdown of equipment for electric power. Use process that draw tree pattern here measuring above zero to study special quality of this electricity tree, real-time processing by image processing is proposed because reproduction of tree blazing fire process drops and pattern of tree is difficult correct quantification of tree growth by existent visual observation by involution. This research presents general process that need in image processing of tree blazing fire, and that remove various noises that happen in above zero by measuring electrical tree dividing background and complete view in measured above zero taking advantage of specially proposed complete view object abstraction techniques effectively and quantification of tree becomes easy naturally, can apply to dielectric breakdown estimate because can chase growth process of tree.

• 정보처리학회논문지B
• /
• 제13B권2호
• /
• pp.83-88
• /
• 2006

일정한 형태의 물체를 분석하기 위해 사용되는 각-거리 그래프를 이용하여 임의의 물체의 경계선 내부 영역의 면적을 측정하는 디지털 영상처리 알고리듬을 제안한다. 물체의 경계선 내부의 한 점을 중심으로 1차 각-거리 그래프를 생성하고 이 그래프로부터 거리 값이 급격히 변화하는 위치를 추출하여 1차 그래프에서 접근하지 못한 영역을 인식하여 새 영역에서의 한 점을 중심으로 2차 각-거리 그래프를 생성한다. 물체의 형태가 복잡한 경우 차수가 증가하게 되며 이와 같이 계층적으로 구성된 각-거리 그래프 그룹에 대해 거리의 제곱을 각도 방향으로 적분하여 물체의 경계선 내부 영역의 면적을 측정한다.

• 대한전자공학회논문지SP
• /
• 제49권4호
• /
• pp.16-22
• /
• 2012

본 논문에서는 어안렌즈의 교정(calibration)과 기하학적 왜곡을 보정하기 위해서 광학 시뮬레이터에 적합한 나선형 패턴을 제안하고, 이를 이용하여 별도의 수학적 모델링이 필요 없는 교정 알고리듬을 제안한다. 나선형 패턴을 광학 시뮬레이터의 입력 영상으로 이용하여 어안렌즈로 왜곡 시킨 영상에서 기하학적으로 이동된 점들의 정합을 통하여 교정을 수행한다. 이러한 과정에서 나선형 패턴 영상에서 중심으로부터 멀어지는 점들이 어안렌즈의 기하학적 왜곡을 거쳐 이동되는 정보를 왜곡되기 전의 위치와 정합하기 때문에 정확한 교정이 가능한 동시에, 별도의 모델링이 필요 없기 때문에 효율적인 처리가 가능하다. 제안된 기술은 어안렌즈를 이용한 패턴인식 시스템에서 손실 없는 디지털 영상 확대를 통하여 정확한 정보를 추출하는 데에 이용할 수 있다. 또한 넓은 시야각을 필요로 하는 다양한 영상처리 분야에 적용하여 어안렌즈의 교정과 왜곡 보정을 가능하게 한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.346-349
• /
• 2011

In this paper, we design a perceptually invisible dot pattern layout and its recognition scheme, and we apply the recognition scheme into a smart self learning aid for interactive learning aid. To increase maximum information capacity and also increase robustness to the noises, we design a ECC (error correcting code) based dot pattern with directional vector indicator. To make a smart self-learning aid, we embed the micro dot pattern (20 information bit + 15 ECC bits + 9 layout information bit) using K ink (CMYK) and extract the dot pattern using IR (infrared) LED and IR filter based camera, which is embedded in the smart pen. The reason we use K ink is that K ink is a carbon based ink in nature, and carbon is easily recognized with IR even without light. After acquiring IR camera images for the dot patterns, we perform layout adjustment using the 9 layout information bit, and extract 20 information bits from 35 data bits which is composed of 20 information bits and 15 ECC bits. To embed and extract information bits, we use topology based dot pattern recognition scheme which is robust to geometric distortion which is very usual in camera based recognition scheme. Topology based pattern recognition traces next information bit symbols using topological distance measurement from the pivot information bit. We implemented and experimented with sample patterns, and it shows that we can achieve almost 99% recognition for our embedding patterns.

• 생물환경조절학회지
• /
• 제20권2호
• /
• pp.63-71
• /
• 2011

영상처리는 정확한 오이의 형상 및 위치를 인식하기 위하여 형상인식 알고리즘에 대한 연구를 수행하였다. 다양한 오이형상을 인식하기 위한 방법으로는 신경회로망의 연상 메모리 알고리즘을 이용하여 오이의 특정형상을 인식하였다. 형상인식은 실제영상에서 오이의 형상과 위치를 판정할 수 있도록 알고리즘을 개발한 결과, 다음과 같은 결론을 얻었다. 본 알고리즘에서는 일정한 학습패턴의 수를 2개, 3개, 4개를 각각 기억시켜 샘플패턴 20개를 실험하여 연상시킨 결과, 학습패턴으로 복원된 출력패턴의 비율은 각각 65.0%, 45.0%, 12.5%로 나타났다. 이는 학습패턴의 수가 많을수록 수렴할 때, 다른 출력패턴으로 많이 검출되었다. 오이의 특정형상 검출은 $30{\times}30$간격으로 자동검출 되도록 처리하였다. 실제영상에서 자동 검출로 처리한 결과, 오이인식의 처리시간은 약 0.5~1초/1개(패턴) 빠르게 검출되었다. 또한, 다섯 개의 실제 영상에서 실험한 결과, 학습패턴에 대한 다른 출력패턴은 96~99%의 제거율을 나타내었다. 오이로 인식된 출력패턴 중에서, 오검출된 출력패턴의 비율은 0.1~4.2%를 나타내었다. 본 연구에서는 신경회로망을 이용하여 오이의 형상 및 위치를 인식할 수 있도록 알고리즘을 개발하였다. 오이의 위치측정은 실제영상에서 학습패턴과 유사한 출력패턴의 좌표를 가지고, 오이의 위치좌표를 추정할 수 있었다.