• 전자공학회논문지D
• /
• 제36D권11호
• /
• pp.71-81
• /
• 1999

본 논문에서는 새로운 직접 접근 방법과 이진 영상처리를 통해 컬러 영상을 저장하고 재생할 수 있는 디지털 홀로그래픽 정보 저장 시스템을 구현하였다. 직접 접근 방법을 통해 영상 처리를 수행한 결과, raw 파일을 이용하여 영상처리를 수행하는 것보다 광메모리에 저장되는 페이지 수르르 줄일 수 있었으며, 압축된 $128{\times}80{\times}256$ (6.6KB) 해상도의 컬러 영상을 재생할 수 있었다. 또한 문자 파일이나 동영상 파일등과 같이 파일의 종류에 관계없이 입력 데이터가 디지털 홀로그램으로 변환될 수 있음을 보여주었다.

• International journal of advanced smart convergence
• /
• 제9권1호
• /
• pp.113-120
• /
• 2020

Recently, the license plate OCR system has been commercialized in a variety of fields and preferred utilizing low-cost embedded systems using only cameras. This system has a high recognition rate of about 98% or more for the environments such as parking lots where non-vehicle is restricted; however, the environments where non-vehicle objects are not restricted, the recognition rate is about 50% to 70%. This low performance is due to the changes in the environment by non-vehicle objects in real-time situations that occur anomaly data which is similar to the license plates. In this paper, we implement the appropriate anomaly detection based on semi-supervised learning for the license plate OCR system in the real-time environment where the appearance of non-vehicle objects is not restricted. In the experiment, we compare systems which anomaly detection is not implemented in the preceding research with the proposed system in this paper. As a result, the systems which anomaly detection is not implemented had a recognition rate of 77%; however, the systems with the semi-supervised learning based on anomaly detection had 88% of recognition rate. Using the techniques of anomaly detection based on the semi-supervised learning was effective in detecting anomaly data and it was helpful to improve the recognition rate of real-time situations.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2011년도 제43차 동계학술발표논문집 19권1호
• /
• pp.229-232
• /
• 2011

최근 스마트 디바이스 기반의 다양한 콘텐츠 제작 공급에 대한 새로운 마켓 시장 형성과 태블릿 디바이스 기반의 전자책 시장 규모의 확대에 따른 새로운 유형의 디지털 콘텐츠 시장이 형성되고 있다. 디지털 미디어는 정보환경 범위를 종이의 범위에서 벗어나 매체와 연계한 다양한 형태로의 변화뿐만 아니라 서술 방식과 소통방식의 방법에도 변화를 발생하였다. 그리고 지면에서 국한된 아날로그 매체의 물리적, 공간적, 시간적인 한계를 뛰어넘어 다양한 콘텐츠를 손쉽게 접근할 수 있게 만들었다. 이런 환경에서 본문검색 서비스는 아날로그와 디지털 매체의 상호 공존관계를 형성할 수 있다. 본 논문에서는 그림종이문서를 본문검색이 가능한 이미지형태의 디지털문서로 변환해주는 디지털라이징 시스템으로 문자위치정보를 포함하는 광학문자인식(OCR)기능과 인식된 문자의 오류를 수정하는 에디터기능을 통해 추출된 내용을 XML형태로 제공하는 본문검색 시스템을 제안한다. 특히, 문자인식 후처리 공정에서 복수의 관학문자인식(OCR)엔진을 통해 결과 비교와 문자위치 정보 확인 및 편집, 맞춤법 검사 등의 특화된 기능 등은 본 논문에서 가지는 강점으로 디지털문서 구축에 소요되는 시간과 비용을 혁신적으로 절감시켜준다.

• KIEE International Transactions on Electrophysics and Applications
• /
• 제5C권1호
• /
• pp.28-32
• /
• 2005

In the Langmuir-Blodgett (LB) technique, a monolayer on the water surface is transferred onto a substrate, which is raised and dipped through the surface. From this, multilayers can be obtained in which constituent molecules are periodically arranged. The LB technique has attracted considerable interest in the fabrication of electrical and electronic devices. Many researchers have investigated the electrical properties of monolayer and multiplayer films. Dendrimers represent a new class of synthetic macromolecules characterized by a regularly branched treelike structure. Multiple branching yields a large number of chain ends that distinguish dendrimers from conventional star-like polymers and microgels. The azobenzene dendrimer is one of the dendritic macromolecules that include the azo-group exhibiting a photochromic character. Due to the presence of the charge transfer element of the azo-group and its rod-shaped structure, these compounds are expected to have potential interest in electronics and ptoelectronics, especially in nonlinear optics. In the present paper, we give pressure stimulation to organic thin films and detect the induced displacement current.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 제39회 하계학술대회
• /
• pp.1100-1101
• /
• 2008

After lamination process, Isc is increased by sheet reflection. This paper presents the electrical output characteristics by back sheet reflection. The experiments was conducted by using single crystalline and multi crystalline PV module. The reflection area of single crystalline PV module is larger than multi one due to the difference of solar cell manufacturing. The experiments show that the increased performance ratio of single crystalline PV module output power is 1.55% rather than that of multi crystalline PV module output power is 1.13%. In addition, it is expected that the output power of single one rather than multi-one is increased by the lower temperature when the PV module is installed outside. The results can be reconsidered by the test material and test process. Back sheet used for humidity prevention makes PV module output power increasing.

• 한국정보시스템학회지:정보시스템연구
• /
• 제26권3호
• /
• pp.273-293
• /
• 2017

Purpose The purpose of this study is to introduce a framework that helps Muslims to determine whether a food can be consumed. It can complement existing Halal food classification services having a difficulty of constructing Halal food database. Design/methodology/approach The proposed framework includes two components. First, OCR(Optical Character Recognition) technique is utilized to read the food additive information. Second, machine learning methods were used to trained and predicted to determine whether a food can be consumed using the provided information. Findings Among the compared machine learning methods, SVM(Support Vector Machine), DT(Decision Tree), and NB(Naive Bayes), SVM with linear kernel and DT had excellent performance in the Halal food classification. The framework which adopting the proposed framework will enhance the tourism experiences of Muslim tourists who consider keeping the Islamic law most importantly. Furthermore, it can eventually contribute to the enhancement of smart tourism ecosystem.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권9호
• /
• pp.3701-3720
• /
• 2015

A system for the recognition of machine printed Arabic script is proposed. The Arabic script is shared by three languages i.e., Arabic, Urdu and Farsi. The three languages have a descent amount of vocabulary in common, thus compounding the problems for identification. Therefore, in an ideal scenario not only the script has to be differentiated from other scripts but also the language of the script has to be recognized. The recognition process involves the segregation of Arabic scripted documents from Latin, Han and other scripted documents using horizontal and vertical projection profiles, and the identification of the language. Identification mainly involves extracting connected components, which are subjected to Principle Component Analysis (PCA) transformation for extracting uncorrelated features. Later the traditional K-Nearest Neighbours (KNN) algorithm is used for recognition. Experiments were carried out by varying the number of principal components and connected components to be extracted per document to find a combination of both that would give the optimal accuracy. An accuracy of 100% is achieved for connected components >=18 and Principal components equals to 15. This proposed system would play a vital role in automatic archiving of multilingual documents and the selection of the appropriate Arabic script in multi lingual Optical Character Recognition (OCR) systems.

• 한국산업융합학회 논문집
• /
• 제16권4호
• /
• pp.113-117
• /
• 2013

This paper describes a new technology to develop the character recognition technology based on pattern recognition for non-contacting inspection optical lens slant or precision parts, and including external form state of lens or electronic parts for the performance verification, this development can achieve badness finding. And, establish to existing reflex data because inputting surface badness degree of scratch's standard specification condition directly, and error designed to distinguish from product more than schedule error to badness product by normalcy product within schedule extent after calculate the error comparing actuality measurement reflex data and standard reflex data mutually. Developed system to smallest 1 pixel unit though measuring is possible 1 pixel as $37{\mu}m{\times}37{\mu}m$ ($0.1369{\times}10-4mm^2$) the accuracy to $1.5{\times}10-4mm$ minutely measuring is possible performance verification and trust ability through an experiment prove.

• Bulletin of the Korean Chemical Society
• /
• 제29권5호
• /
• pp.933-938
• /
• 2008

2,4-Di-(2'-hydroxyethoxy)benzylidenemalononitrile (3) was prepared and polymerized with terephthaloyl chloride and adipoyl chloride to yield novel Y-type polyesters 4 and 5 containing dioxybenzylidenemalononitrile groups as NLO-chromophores, which constituted parts of the polymer backbone. The resulting polymers 4 and 5 are soluble in common organic solvents such as acetone and N,N-dimethylformamide. Polymers 4 and 5 showed thermal stability up to 300 ${^{\circ}C}$ in thermogravimetric analysis with glass-transition temperatures obtained from differential scanning calorimetry in the range 83-94 ${^{\circ}C}$. The second harmonic generation (SHG) coefficients ($d_{33}$) of poled polymer films at the 1064 nm fundamental wavelength were around $6.48\;{\times}\;10^{-9}$ esu. The dipole alignment exhibited high thermal stability even at 10 ${^{\circ}C}$ higher than $T_g$ and no significant SHG decay was observed below 105 ${^{\circ}C}$ partially due to the main-chain character of polymer structure, which is acceptable for NLO device applications.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2018년도 제58차 하계학술대회논문집 26권2호
• /
• pp.189-190
• /
• 2018

최근에는 여행에 대한 각종 정보가 많이 공유되는 추세이다. 최근 사람들은 소셜 네트워크 서비스를 이용 중이거나 웹 서핑을 하는 도중에 기억하고 싶어 하는 여행지를 단순히 캡처 해놓거나 메모장에 기록해둔다. 이러한 방법은 시간이 지나 많은 데이터가 쌓이면 관리하기 어렵다는 문제가 존재한다. 본 논문에서는 사용자의 편리를 고려하여 사진의 텍스트를 광학식 문자 판독을 활용하여 출력하고 게시 글 형태로 저장할 수 있게 개발하였다. 명소의 위치 또한 자동완성 위치 검색 라이브러리를 통하여 편리 저장이 가능하다. 위치 데이터를 통해 향후 사용자가 근접하고 있는 여행지 또한 제공해줄 수 있도록 구현하였다. 이를 위하여 웹을 통해서 이용할 수도 있으며 실시간 검색과 알림 이벤트를 위해 웹 주소 입력 없이도 앱을 실행할 수 있는 프로그래시브웹 앱을 구현하였다.