• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2010년도 춘계학술대회 논문집
• /
• pp.283-284
• /
• 2010

• 한국정밀공학회지
• /
• 제22권5호
• /
• pp.7-15
• /
• 2005

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.1129-1131
• /
• 2008

We injection molded a plate with micro surface features including micro prizms & micro channels patterns on its surface and investigated the replication of the micro features depending on the mold temperature which is one of typical process parameters. The size of the patterns were 8um, 10um, 15um of prizm features & 15um, 30um, 45um of channel features. The size of the plate is about $400mm{\times}400mm$ and the thickness is 1mm of plate. the repliction of the mucro features turned out to depend on the mold temperature and also the location on the plate. The pressure and the feature of the melt in the cavity were also measured in real-time for the investigation on the micro feature replication.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.41.5-41
• /
• 2002

This paper presents a feature extraction algorithm for vision-based micromanipulation. In order to guarantee of the accurate micromanipulation, most of micromanipulation systems use vision sensor. Vision data from an optical microscope or high magnification lens have vast information, however, characteristics of micro image such as emphasized contour, texture, and noise are make it difficult to apply macro image processing algorithms to micro image. Grasping points extraction is very important task in micromanipulation because inaccurate grasping points can cause breakdown of micro gripper or miss of micro objects. To solve those problems and extract grasping points for micromanipulation...

• 한국정밀공학회지
• /
• 제28권5호
• /
• pp.578-584
• /
• 2011

In mechanical cutting process, burr was generated at workpiece by cutting tool generally. It is working disturbance during manufacturing process. Besides burr was taken shape relatively large size more micro scale machining than macro scale machining. Many researches have been studied to remove micro burr(de-burring), because it was negative effect for accuracy of machining shape. However, micro de-burring was constrained by burr height, micro feature and so on. In this paper, experimental research was carried out to compare de-burring characteristics of $Al_2O_3$ abrasive and polymer.

• 융합보안논문지
• /
• 제14권5호
• /
• pp.17-24
• /
• 2014

본 논문에서는 얼굴 표정 인식을 위한 지역미세패턴(local micro pattern)의 하나인 LBP(Local Binary Pattern) 코드의 잡음에 대한 단점을 해결하기위하여 새로운 미세패턴 방법인 LDP(Local Directional Pattern)를 제안한다. 제안된 방법은 LBP의 문제점을 해결하기 위해 $m{\times}m$ 마스크를 이용하여 8개의 방향 성분을 구하고, 이를 크기에 따라서 정렬한 후 상위 k개를 선정하여 해당 방향을 나타내는 비트를 1로 설정한다. 그리고 8개의 방향 비트를 순차적으로 연결하여 최종 패턴 코드를 생성한다. 실험결과, 제안된 방법은 기존 방법에 비해 회전에 대한 영향이 적으며, 잡음에 대한 적응력이 현저히 높았다. 또한, 제안된 방법을 기반으로 얼굴의 영구적인 특징과 일시적인 특징을 함께 표현하는 새로운 지역미세패턴의 개발이 가능함을 확인하였다.

• 한국음향학회지
• /
• 제38권6호
• /
• pp.687-696
• /
• 2019

기존의 지진파 분류 특징은 강진에 초점이 맞추어져 있어서 미소지진과 같은 지진파는 다소 적합하지 않다. 본 연구에서는 강진과 더불어 미소지진, 인공지진, 잡음 분류에 적합한 특징 추출을 위해 주파수-시간 공간 내에서 히스토그램과 주성분 기반 특징 추출방법을 제안한다. 제안된 방법은 지진파의 주파수 관련 정보와 시간 관련 정보를 결합하는 방법을 적용한 히스토그램 기반 특징 추출방법과 주성분 기반 특징 추출방법을 이용하여 지진(강진, 미소지진, 인공지진)과 잡음, 미소지진과 잡음, 미소지진과 인공지진을 이진 분류한다. 2017년~2018년 최근 국내지진 자료와 분류 성능을 토대로 제안한 특징 추출방식의 효용성을 비교 평가한다.

• 한국정밀공학회지
• /
• 제33권9호
• /
• pp.715-721
• /
• 2016

In this paper, the classification rate of micro-cracks in silicon wafers was improved using a SVM. In case I, we investigated how feature data of micro-cracks and SVM parameters affect a classification rate. As a result, weighting vector and bias did not affect the classification rate, which was improved in case of high cost and sigmoid kernel function. Case II was performed using a more high quality image than that in case I. It was identified that learning data and input data had a large effect on the classification rate. Finally, images from cases I and II and another illumination system were used in case III. In spite of different condition images, good classification rates was achieved. Critical points for micro-crack classification improvement are SVM parameters, kernel function, clustered feature data, and experimental conditions. In the future, excellent results could be obtained through SVM parameter tuning and clustered feature data.

• 소성∙가공
• /
• 제19권3호
• /
• pp.191-196
• /
• 2010

Tungsten-carbide as typical difficult-to-cut material has excellent mechanical properties such as high thermal resistivity, mechanical strength and chemical durability. However, it is next to impossible for tungsten-carbide to be fabricated the needed parts by cutting process. In this study, for establishing the micro fabrication method of tungsten-carbide for micro injection or compression molding core, the investigation on micro cutting characteristics of tungsten-carbide green part which is made by powder injection molding process and easy to cut relatively was performed. For this, micro endmilling experiments of tungsten-carbide green part were performed according to various cutting conditions. Finally, the wear trend of micro endmill and the appearance of micro rib according to feed-rate and cutting depth per step were analyzed through SEM images of micro cutting feature and microscope images of micro tools.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2007년도 춘계학술대회 논문집
• /
• pp.75-78
• /
• 2007

Recently, the need for micro mold or micro mechanical parts has been rapidly increased. As feature size decreases, conventional machining processes show their limitation. Micro electrical discharging machining (EDM) and electrochemical machining (ECM) have many advantages in micro machining. They can be used to make structures of micro scale, or even nano scale size. In this paper, the application of micro EDM and ECM has been investigated.