• Food Science and Biotechnology
• /
• 제17권1호
• /
• pp.58-65
• /
• 2008

To see the possibility of irradiation as an alternative to ultra high temperature (UHT) sterilization, the quality characteristics of milk were analyzed. Milk treated by UHT ($135^{\circ}C$ for 4 sec) and irradiation at higher than 3 kGy showed no viable counts after 7 days of storage at $4^{\circ}C$. The contents of certain amino acids of milk, such as Arg, Asp, Glu, Ile, Leu, Lys, Pro, Ser, Thr, and Tyr, were lower in irradiated groups at 10 kGy than in UHT-treated one, but no difference was observed between irradiated milks at less than 5 kGy and UHT. The capillary electrophoresis (CE) patterns of the milk irradiated at 10 kGy showed a similar trend to the raw milk, low temperature long time (LTLT, $63^{\circ}C$ for 30 min), and high temperature short time (HTST, $72^{\circ}C$ for 15 sec) treated. However, the CE pattern of UHT-treated milk was different. Rennet coagulation test agreed with the CE results, showing that all milk samples were coagulated by rennet addition except for UHT-treated milk after 1 hr. These results suggest that irradiation of milk reduce the content of individual amino acids but it may not induce severe conformational change at a protein level when compared with UHT treatment.

• 정보처리학회논문지B
• /
• 제13B권4호
• /
• pp.429-438
• /
• 2006

일반적으로 신경망은 비선형성 문제를 해결하기 위해서 소프트웨어로 많이 구현되었지만, 영상처리 및 패턴인식과 같은 실시간 처리가 요구되는 응용에서는 빠른 처리가 가능한 하드웨어로 구현되고 있다. 다양한 종류의 신경망 중에서 다층 신경망(MLP: multi-layer perceptron)의 하드웨어 설계는 빠른 처리속도와 적은 면적 그리고 구현의 용이성으로 고정소수점 연산을 많이 사용하였다. 하지만 고정소수점 연산을 사용하는 하드웨어 설계는 높은 정확도의 부동소수점 연산을 많이 사용하는 소프트웨어 MLP를 쉽게 적용할 수 없는 문제점을 가진다. 본 논문에서는 높은 정확도와 높은 유연성을 가지는 부동소수점 연산을 사용하면서도 은닉층 뉴런수를 주기(cycle)로 빠르게 수행하는 MLP의 완전 파이프라이닝(fully-pipelining) 설계방법을 제안한다. MLP는 주어진 문제에 의해서 자연스럽게 입력층과 출력층의 구조가 결정되지만, 은닉층 구조는 사용자에 의해서 결정된다. 그러므로 제안된 설계방법은 많은 반복수행이 요구되는 영상처리 및 패턴인식 등의 분야에서 은닉층 뉴런수를 최적화 하여 쉽게 성능 향상을 이룰 수 있다.

• 한국산업정보학회논문지
• /
• 제12권2호
• /
• pp.60-67
• /
• 2007

본 연구에서는 영상처리 및 패턴인식기법의 온라인 교육을 위한 컴퓨터 비전 실습에 대한 사례 연구를 다룬다. 컴퓨터 비전 실습내용은 원격 영상획득방법, 기초 영상처리 및 패턴인식방법, 렌즈 및 조명 선택방법, 통신을 포함한다. 본 연구는 원격 학습환경에서의 컴퓨터 비전 실습교육에 대한 사례연구로써, 원격 실습환경 구축방법과 영상처리 실습사례들이 소개되었다. 인터넷 환경구축보다는 원격 환경에 적합한 컴퓨터 비전실습 내용과 방법에 본 연구의 주안점을 두었다. 마지막으로, 온라인 컴퓨터 비전실습을 향상시킬 수 있는 방법과 추후연구과제를 제안하였다.

• 한국정보처리학회논문지
• /
• 제3권5호
• /
• pp.1138-1146
• /
• 1996

퍼지 논리는 추론과정에서 일부의 정보가 무시되어 적절하지 못한 추론 결과를 초래할 수 있다. 한편, 신경망은 패턴 처리에는 적합하지만 인간의 지식을 모델링하기 위해서 필요한 논리적인 추론에는 부적합하다. 그러나 신경망의 변형인 신경논리망 (neural logic network)을 이용하면 논리적인 추론이 가능하다. 따라서 본 논문에서는 기존의 신경논리망을 기반으로 하는 추론 네트워크를 확장하여 퍼지추론 네트워크(fuzzy inference network)를 구성한다. 그리고 기존의 추론 네트워크에서 사용되는 전파규칙 (propagation rule)을 보완하여 적용한다. 퍼지추론 네트워크 상에서 퍼지 규칙의 실행부에 해당하는 명제의 믿음값을 결정하기 위해서는 추론하고자 하는 명제에 연결된 노드들을 탐색해야 한다. 이를 위해서 연결된 모든 노드들의 링크를 따라 순차적인 탐색을 하는 경우와 링크에 부여된 우선순위에 의해 탐색을 하는 경우의 탐색비용에 대하여 실험을 통해 비교·평가한다.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 1999년도 춘계학술대회논문집
• /
• pp.199-202
• /
• 1999

Many processing times for fabricating complex shaped parts by near net shape process such as thixoforming or semi-solid forming, are required due to the time for die design, induction heating and forming process. Therefore, for the thixoforming process, multi-capacity induction heating process is very important due to the reduction of the processing time and cost. It is indispensable to adopt a power-time heating pattern which manages to conciliate complete eutectic melting at the core with limited overheating at the periphery. The total reheating time is thus dependent on billet diameter; in inches$(pm20%)$. Typically, high frequency is used for the rapid reheating of the billet to the eutectic temperature range and low frequency for the remelting of the desired fraction of liquid and for the radial homogeneization of the liquid fraction. So in this study, the multi-capacity induction heating conditions of ALTHIX 86s alloy to reduce the processing time and cost would be proposed. The suitability of multi-capacity induction heating conditions would be verified through the comparison to Garat's data.

• Asian-Australasian Journal of Animal Sciences
• /
• 제18권8호
• /
• pp.1194-1198
• /
• 2005

A computer vision system was designed and validated to recognize an individual Holstein cattle by processing images of their body patterns. This system involves image capture, image pre-processing, algorithm processing, and an artificial neural network recognition algorithm. Optimum management of individuals is one of the most important factors in keeping cattle healthy and productive. In this study, an image-processing system was used to recognize individual Holstein cattle by identifying the body-pattern images captured by a charge-coupled device (CCD). A recognition system was developed and applied to acquire images of 49 cattles. The pixel values of the body images were transformed into input data comprising binary signals for the neural network. Images of the 49 cattle were analyzed to learn input layer elements, and ten cattles were used to verify the output layer elements in the neural network by using an individual recognition program. The system proved to be reliable for the individual recognition of cattles in natural light.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.780-791
• /
• 1996

A hybrid image processing system which automatically distinguished lean tissues in the image of a complex beef cut surface and generated the lean tissue contour has been developed. Because of the in homegeneous distribution and fuzzy pattern of fat and lean tissue on the beef cut, conventional image segmentation and contour generation algorithm suffer from a heavy computing requirement, algorithm complexity and poor robustness. The proposed system utilizes an artificial neural network enhance the robustness of processing. The system is composed of pre-network , network and post-network processing stages. At the pre-network stage, gray level images of beef cuts were segmented and resized to be adequate to the network input. Features such as fat and bone were enhanced and the enhanced input image was converted tot he grid pattern image, whose grid was formed as 4 X4 pixel size. at the network stage, the normalized gray value of each grid image was taken as the network input. Th pre-trained network generated the grid image output of the isolated lean tissue. A training scheme of the network and the separating performance were presented and analyzed. The developed hybrid system showed the feasibility of the human like robust object segmentation and contour generation for the complex , fuzzy and irregular image.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 1999년도 춘계학술대회 논문집
• /
• pp.712-715
• /
• 1999

Treeing has a profit to observe processing electrical breakdown because it gives degradation steps of insulation material by optical method. But, reappearance properly of treeing is not so good and precise quantization of tree growth is not so easy because tree Patterns are very complicate. The study on tree growth using image processing is predicted to precision of tree degradation and possible to quality measurement of tree pattern. In this paper, degradation steps are analyzed by image processing, therefore precision and realiability of tree growth are increased. Also, processing of tree degradation is quantized by fractal.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1991년도 춘계학술대회
• /
• pp.51-55
• /
• 1991

This paper describes an algorithm of pattern analysis of ECG signals by significant points extraction method. The significant points can be extracted by modified zerocrossing method, which method determines the real significant point among the significant point candidates by zerocrossing method and slope rate of left side and right side. This modified zerocrossing method improves the accuracy of detection of real significant point position. This paper also describes the pattern matching algorithm by a hierarchical AND/OR graph of ECG signals. The decomposition of ECG signals by a hierarchical AND/OR graph can make the pattern matching process easy and fast. Furthermore the pattern matching to the significant points reduces the processing time of ECG analysis.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.126-131
• /
• 2004

The popularity of flat-panel display(FPD), including plasma display panel(PDP) and liquid-crystal display(LCD), has given rise to the need to streamline their production. In these days, PDP is one of the most popular display devices because of its expansion of manufacturing process and simplicity. Bus electrodes, sustain electrodes, barrier ribs and RGB phosphors are patterned on PDP panel to display an image. Since a minute damage on the pattern can cause a serious defect to display, it is important to inspect the pattern precisely. In this paper, an automatic inspection system of repeated pattern in PDP panel has been introduced to find the defect, such as open, short, dirt, island, and so on. And the inspection system has been operated in the mass production line of PDP.