• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.380-383
• /
• 2008

본 논문은 단순한 키워드 검색에서 발생하는 오차를 줄이기 위해 이미지의 코너정보와 그레이스케일 히스토그램 정제를 이용한 영상 검색 시스템을 구현하고자 한다. 먼저 원하는 이미지의 특정을 추출하는 단계와 추출된 특징을 분석하는 단계, 확보된 정보를 데이터베이스로부터 검색하는 단계, 그 결과 안에서의 그레이스케일 히스토그램 정제 방법으로 다시 재검색하는 단계, 마지막으로 정확한 정보 추출단계를 거치게 된다. 구현 알고리즘은 검색 단계에 있어서 크게 2단계로 나눠진다. 먼저 이미지를 에지로 변환 코너정보를 추출하는 단계, 코너 점의 픽셀을 3*3으로 나누어 RGB중의 픽셀의 합을 하는 단계, 그 코너 값을 데이터베이스와 비교하는 단계, 최대 500개까지의 추출된 이미지를 데이터베이스에 저장되는 단계로 이루어지며 다음 단계는 원 이미지를 그레이스케일로 변환 등질화하는 단계, 히스토그램 정보 획득하는 단계, 8*8 개의 빈으로 나누어 최대 색상정보 값을 추출하는 단계, 그리고 최대 색상정보 영역을 1단계 결과 값과 비교하여 정확한 검색을 얻는 단계로 구성되며 시뮬레이션 결과는 우수한 정확도를 보여 주고 있다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.4
• /
• pp.40-47
• /
• 1997

This paper proposes a method using the straight line Hough transform(SLHT) that recognizes the position of DNA band images from the scanner. The method also detects and corrects automatically the leaning angle of the image. After binarization of a gray-scale DNA band images, the SLHT detects line components involved in the image and recognizes the position of the image using the cross paints of the line components assuming the image is in retangular shape. To improve efficiency of reading many IINA band images through the scanner, this method finds and corrects the leaning angle accurately as less than -t I degree.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.8
• /
• pp.83-88
• /
• 2004

The Classification of defected oil-seals using a vision system with the artificial neural network is presented. The artificial neural network fur classification consists of 27 input nodes, 10 hidden nodes, and one output node. The selection of the number of the input nodes is based on an observation that the difference among the defected, non-defected, and smeared oil-seals is greatly pronounced in the 26 step gray-scale level thresholding. The number of the hidden nodes is chosen as a result of a trade-off between accuracy and computing time. The back-propagation algorithm is used for teaching the network. The proposed network is capable of successfully classifying the defected from the smeared oil-seals which tend to be classified as the defected ones using the binary thresholding. It is envisaged that the proposed method improves the reliability and productivity of the automotive vision inspection system.

• Journal of Korean Society of Water and Wastewater
• /
• v.28 no.3
• /
• pp.305-314
• /
• 2014

A pilot plant (Q=5 $m^3/d$) study was implemented for small and medium sized personal wastewater treatment plant effluent to evaluate MBR and A/O processes utilizing self-sufficient energy composed of wind and solar energy. The removal efficiencies of BOD, SS, turbidity and color were sufficient for legal water quality standards for gray water. However, those of nitrogen and phosphorus could not meet legal regulations which suggested that further removal of those contaminants were needed for reuse of the treated water. Self-sufficient energy rate was 100 % for the pilot plant due to excessive design capacity. In this research, wind and solar energy system was applied considering geological characteristics, which significantly improved energy self-sufficiency. Substantial improvement on energy self-sufficiency can be obtained by optimized investment and operation at a full scale wastewater treatment plant.

• Biomedical Science Letters
• /
• v.11 no.1
• /
• pp.23-29
• /
• 2005

Molecular imaging with targeted contrast agents enables tissues to be distinguished by detecting specific cell-surface receptors. In the present study, a ligand-targeted acoustic nanoparticle system is used to identify angioplasty-induced expression of tissue factor by smooth muscle cell within carotid arteries. Pig carotid arteries were overstretched with balloon catheters, treated with tissue factor-targeted or a control nanoparticle system, and imaged with intravascular ultrasound before and after treatment. Tissue factor-targeted emulsion bound and increased the echogenicity and gray-scale levels of overstretched smooth muscle cell within the tunica media, versus no change in contralateral control arteries. Expression of stretch-induced tissue factor in carotid artery media was confirmed by immunohistochemistry. The potential for abnormal thrombogenicity of balloon-injured arteries, as reflected by smooth muscle expression of tissue factor, was imaged using a novel, targeted, nanoparticulate ultrasonic contrast agent.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.3
• /
• pp.176-180
• /
• 2011

Even though algorithms for watermark embedding and extraction step are important issue for digital watermarking, watermark selection and post-processing can give us an opportunity to improve our algorithms and achieve higher performance. For this reason, we summarized the possibilities of improvements for digital watermarking by referring to the watermark merging techniques rather than embedding and extraction algorithms in this paper. We chose Cox's function as main embedding and extraction algorithm, and multiple barcode watermarks as a watermark. Each bit of the multiple copies of barcode watermark was embedded into a gray-scale image with Cox's embedding function. After extracting the numbers of watermark, we applied the watermark merging techniques; including the simple merging, N-step iterated merging, recover merging and combination of iterated-recover merging. Main consequence of our paper was the fact of finding out how multiple barcode watermarks and merging techniques can give us opportunities to improve the performance of algorithm.

• Proceedings of the KIEE Conference
• /
• 2000.11c
• /
• pp.449-451
• /
• 2000

Crosstalk is the primary cause of image distortion in active matrix liquid crystal displays (AMLCD). Crosstalk produces voltage errors that limit gray scale fidelity and consequently, degrades display resolution, contrast ratio, color fidelity, and image quality. In this study, crosstalk phenomena of some methods to compensate level shift voltages has been simulated. This will be contributed to find the way to design the excellent image quality of the TFT-LCDs.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.1
• /
• pp.197-208
• /
• 2016

In this paper, we propose a method based on a convolutional neural network which is one of the deep neural network. So, we convert a malware code to malware image and train the convolutional neural network. In experiment with classify 9-families, the proposed method records a 96.2%, 98.7% of top-1, 2 error rate. And our model can classify 27 families with 82.9%, 89% of top-1,2 error rate.

• 한국연소학회:학술대회논문집
• /
• 2004.06a
• /
• pp.67-74
• /
• 2004

Numerical analysis code has been developed for investigating the combustion characteristics in a slab heater of a steel mill company. Unsteady full 3-Dimensional behaviour can be predicted with the code. Premixed flame model is adopted for combustion phenomena. And eddy dissipation model is used for turbulent flow and non gray FVM method for radiation. Slab movement can be fully traced from entrance into heater until it's exit and computation is performed during that period. Code was validated by comparing the calculation results with experimental ones for the bench scale heater.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.869-873
• /
• 2007

본 논문은 고속으로 생산되는 제품의 영상을 캡쳐한 후 영상처리 기법 중 에지 추출 알고리즘을 응용하여 조명에 투과된 제품의 에지를 추출 및 필터링 하는 방법으로 결함 검출 시스템을 설계한다. 소형의 임베디드 기기에 패턴 매칭 영상처리 기법을 이용하여 결함을 검출하고 패턴의 비 매칭 정도를 기준점에 따라 정상 또는 불량 판정을 할 수 있는 어플리케이션을 개발하고 탑재하였고, 어플리케이션의 불량 판정 알고리즘으로는 NGC (Normalized GrayScale Corelation) 기법을 사용하였고 검출 판정 결과 적절한 판정값을 입력하는 것으로 기준 패턴과 형상이 다른 대상의 불량을 판정한다.