• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.7-11
• /
• 2012

This paper develops the coin recognition and classification system using digital image processing technique. Coin images are taken by USB camera. The developed system can be used at home since it just needs USB camera and personal computers. For this development, some digital image prodessing technique is used; size recognition technique and color classification. Using Matlab, we design the graphic user interface and verify the reliability of the developed system with some simulation result.

• Journal of Platform Technology
• /
• v.9 no.3
• /
• pp.63-69
• /
• 2021

Limited materials to make coins for countries and designs suitable for hand-carry make the shape, size, and color of coins similar. This similarity makes that it is difficult for visitors to identify each country's coins. To solve this problem, we propose the coin classification method using CNN effective to image processing. In our coin identification method, we collect the training data by using web crawling and use OpenCV for preprocessing. After preprocessing, we extract features from an image by using three CNN layers and classify coins by using two fully connected network layers. To show that our model designed in this paper is effective for coin classification, we evaluate our model using eight different coin types. From our experimental results, the accuracy for coin classification is about 99.5%.

• KIISE Transactions on Computing Practices
• /
• v.21 no.6
• /
• pp.424-429
• /
• 2015

This research proposes a new system for calculating the total amount of coins in an image. The proposed system identified and classified the coins in the image in realtime. The image was obtained using a USB camera. Most previous coin calculation systems only used size information. If the size of an object was incorrectly detected, it caused a misclassification. Especially, in case of the former 10 won, it had high error rate because it was similar in size to the 50 won and 100 won coin. The proposed system combines hue histogram information with size information to reduce errors in the classification process. When we only used size information in the classification experiment of 2,290 coins, the recognition rate was on average about 88.2%. When we combined hue information with size information the recognition rate increased to about 99.3%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.320-322
• /
• 2020

기계학습은 인공지능의 한 클래스로 최근 이미지 및 음성인식, 지능적 웹 검색, 자율 주행 자동차 등의 영역에서 성공적 발전을 바탕으로 우리의 일상에 폭넓게 이용되고 있다. 본 논문에서는 Keras 오픈소스 라이브러리를 이용해 딥러닝을 이용한 기계학습 기반의 동전 인식 소프트웨어를 구현하였고, 이를 이용해 동전 자동분류 스마트 저금통을 설계하였다. 동작 검증을 위하여 스마트 저금통의 모든 발생 이벤트는 Parse-server와 mongoDB를 이용하여 시각화 및 어플리케이션 및 웹사이트를 연결하였다.

• 보존과학연구
• /
• s.8
• /
• pp.1-12
• /
• 1987

Fifty ancient Korean coins originated in Choson dynasty have been determined for 9 elements such as Sn, Fe, As, Ag, Co, Sb, Ir, Ru and Ni by instrumental neutron activation analysis and for 3 elements such as Cu, Pb, and Zn by atomicalsorption spectrometry. Bronze coins originated in early days of the dynasty contain as major constituents Cu, Pb and Sn approximately in the ratio 90 : 4 : 3, where as, those in latter days contain in the ratio 7 : 2 : 0. Brass coins which had begun in 17century contain as major constituents Cu, Zn and Pb approximately in the ratio 7 : 1: 1. The multivariate date have been analyzed for the relation among elemental contents through the variance-covariance matrix. The data have been fur theranalyzed by a principal component mapping method. As the results training set of 8class have been chosen, based on the spread of sample points in an eigenvector plotand archaeolgical data such as age and the office of minting.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1207-1208
• /
• 2017

'스마트 저금통' 이란 많은 사람들이 일상생활에서 흔히 쓰는 저금통을 IoT기술과 접목시켜 더욱 편리하게 사용할 수 있게 만든 스마트 저금통이다. 화폐(지폐, 동전)인식 및 분류, 저금통과 앱 간의 연동을 통한 손쉬운 금액관리 및 다양한 부가 서비스를 제공하고, 스마트폰을 활용한 가상화폐전환 및 간편결제 등의 핀테크를 통한 저축 및 쇼핑 등이 가능하다.

• Asian Journal of Turfgrass Science
• /
• v.25 no.2
• /
• pp.171-176
• /
• 2011

Sclerotinia homoeocarpa, the causal agent of dollar spot, is one of the most common pathogens of cool season turfgrasses in South Korea. The vegetative compatibility group (VCG) assay was carried out using nitrate-nonutilizing (nit) mutants recovered from 13 South Korean isolates with various geographical origins. The mutants were divided into four phenotypic classes based on mutation loci associated with nitrogen assimilation: nit1, nit2, nit3, and NitM. The recovered number of nit mutants greatly varied among the isolates, ranging from 0 to 15 mutants. Of the mutants isolated, nit1 and nit2 mutants were most common (80%) while NitM and nit3 were relatively rare. One dominant and four minor VCGs were determined from 18 mutant isolates tested. To study population structures of Korean S. homoeocarpa isolates and increase our understanding of its ecological and epidemiological aspects for dollar spot management on turfgrass, more generated mutants should be tested with more diverse isolate collections.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.14 no.3
• /
• pp.245-251
• /
• 2016

Soil can be contaminated by radioactive materials due to nuclide leakage following unexpected situations during the decommissioning of a nuclear power plant. Soil decontamination is necessary if contaminated land is to be reused for housing or industry. The present study classifies various soil remediation technologies into biological, physics/chemical and thermal treatment and analyzes their principles and treatment materials. Among these methods, this study selects technologies and categorizes the economics, applicability and technical characteristics of each technology into three levels of high, medium and low by weighting the various factors. Based on this analysis, the most applicable soil decontamination technology was identified.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 2001.11a
• /
• pp.57-58
• /
• 2001

용수 다소비 산업으로 분류되는 제지공업의 특성 상, 용수사용의 억제 및 용수의 무방류화에 대한 압력이 증가되고 있는 반면, 초지환경은 날로 열악해지고 있는 실정이다. 한 예로써, 용지의 재활용율 및 재사용 비율이 증가함에 따라 원료의 저급화가 심 각한 수준에 이르고 있으며, 이러한 초지환경의 변화는 각질화되고 극도로 미세화된 다량의 미세섬유 발생 및 잡고지로부터 유입되는 점착성 이물질과 무기 충진제의 도입 등을 유발함으로서 제품의 물리적 성질 저하, 탈수부하 증가로 인한 생산성 저하, 약품사용량 증가 등을 초래하여, 결과적으로는 폐수처리장의 부하를 증대시킴과 동시에 청수사용량 및 폐수방류량을 증가시키는 악순환을 되풀이하게 된다. 국내 제지산업이 국제적 경쟁력을 갖추기 위해서는 제품의 증대가 필수적이나, 원료와 설비의존도를 감안할 때, 제품특성과 공정 분을 결정하는 습부공정을 정확히 파악하여 최적 운전조건을 확립하는 것이 가장 경제적이고 용이한 방법일 뿐만 아니라 전체 제지공정의 정정화에도 기여할 수 있을 것으로 판단된다. 일정규모이상의 종이를 생산하는 제지공장은 거의 대부분 컴퓨터로 처리되는 온라인 공정조절 시스템(On-line process control system)을 구비하고 료의 도입에서부터 설비운전 및 제품의 기본적인 품질관리까지 실시간의 자동화되고 안정적인 운전과 관리시스템을 유지하고 있다. 그러나 전체 제지공정 중, 제품 물성과 운전조건의 대부분을 결정하는 습부공정만큼은 아직도 주기적인 분석이 행해지고 있지 않을 뿐만 아니라, 슬러리의 농도나 보류도 정도를 제이하면 분석항목 조차도 변변히 확립되어 있지 않을 실정이다. 이는 다량의 물 속에 존재하게 되는 용전물질(Dissolved solids, DS), 부유물질(Suspended solids, SS), 섬 유(Fibers), 무기 미 세분(Inorganic f fines), 그리고 투입되는 약품간에 발생하는 계면동전현상 및 이러한 현상과 최종 지제 품의 물성간의 상관관계에 대한 이해 정도나 경험 부족에서 기인하는 것으로 생각된다. 1 1983년 미국제지기술연합회(T APpI)의 제지용 첨가제 분과위원회(Papermaking A Additive Committee)에서는 습부공정의 적절한 조절을 위해 어떤 항목들이 필요하며 그 중요도는 어떠한가를 조사하였으며, 그 결과로 전하밀도, 제타전위, 보류도 및 여수 도, 무기 미세분 함량 등이 중요하다고 보고하였다. 그러나 지료의 전기적 특성을 실시 간으로 측정하는 기자재류가 최근에 이르러서야 도입되고 있는 실정이기 때문에 충분 한 현장적용 사례가 보고되지 못하고 있으며, 결과적으로 얻어진 정보와 최종 지제품의 물성 및 초지기 운전조건과의 상관관계를 확립하는 작업결과는 더욱 찾아보기 어렵다. 따라서, 본 연구에서는, 라이너지 제조공장의 습부공정에 투입되는 약품이 지료 의 전기적 성질, 즉 전하밀도와 제타전위에 미치는 영향을 모니터링함으로서 지료의 전기적 성질들과 습부 공정상태와의 상관관계를 살펴보고자 하였다. 본 연구는 다음과 같은 순서로 진행하였다.

• Korean journal of applied entomology
• /
• v.44 no.3 s.140
• /
• pp.177-187
• /
• 2005

For the comparison of feeding behavior of Nilaparvata lugens among different rice varieties, electrical penetration graph (EPG) technique was used. Ten rice varieties were selected from national-widely recommended rice varieties cultivating in Chungnam province. The correlation between feeding duration and honeydew amount excreted was investigated, and the types of EPG pattern were analyzed among rice varieties. The EPG patterns divided into 6 types according to electrical specific feature, respectively. Type 1 pattern was a searching feeding sites, resting or wandering on a rice plant. Type 2 pattern was appeared when the insect untaken from phloem sieve element. Type 3 pattern was observed when the insect piercing into the rice plant. Type 4 pattern was observed when the insect salivating in rice plant. Type 5 pattern was observed when the insect ingesting from the xylem. Type 6 pattern was observed when the stylet moving in cell. Feeding duration time on Gum-nam was significantly shorter than Dong-jin, Dae-ahn, Dong-ahn, Dae-san. Also, on Gun-nam, it was shown that the brown planthopper did not penetrate the cuticle for a long time. The total number of excreted honeydew droplets by the brown planthopper was the greatest in Dong-jin variety and the least in Gum-nam variety. In proportion to phloem feeding time, the number of honeydew droplets had been increased. According to the results of EPG patterns and honeydew droplets analysis, N. lugens seems to prefer Dong-jin, Dong-ahn, Dae-san, and Dae-ahn to Gum-nam, Da-san, and Nam-chun rice plant variety.