• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.1
• /
• pp.39-55
• /
• 2013

It is a difficult problem to use keyword retrieval for low-quality Korean document images because these include adjacent characters that are connected. In addition, images that are created from various fonts are likely to be distorted during acquisition. In this paper, we propose and test a keyword retrieval system, using a support vector machine (SVM) for the retrieval of low-quality Korean document images. We propose a keyword retrieval method using an SVM to discriminate the similarity between two word images. We demonstrated that the proposed keyword retrieval method is more effective than the accumulated Optical Character Recognition (OCR)-based searching method. Moreover, using the SVM is better than Bayesian decision or artificial neural network for determining the similarity of two images.

• Structural Engineering and Mechanics
• /
• v.42 no.5
• /
• pp.747-760
• /
• 2012

In today's online social structure, people with electronic devices or network have been closely related to whether any of the activities, work, school, etc., is related to electronic devices, intelligent robot, and network control. The best mobility and the first rich media of these products as smart phones, smart phones rise rapidly in recent years, high speed processing performance and high free way to install software, deeply loved by many business people. However, not only for smart phone business aspects of the use, but also can engage in education of the teachers or the students are learning a great help. This study construct OCR-assisted learning software written by the JAVA made, and the installation is provided by the Android mobile phone users.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.293-294
• /
• 2020

본 논문에서는 현재 이슈가 되고 있는 개인 정보 보안에 대해서 Keras 라이브러리를 사용하여 개인 정보 관련 데이터를 학습한 후, 한글 인식률 증가된 Tesseract-OCR 활용하여 사람들이 가지고 있는 데이터의 개인 정보 유무를 판단하여 분류한다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.220-221
• /
• 2022

선박에선 의료관리자가 선박 의약품의 처방 및 관리를 하고 있으며 이는 대부분 항해사로 지정된다. 항해사의 고유 업무와 전문의료지식 부족으로 의약품 관리가 체계적으로 이루어지지 않고 수기로 기록되는 문제점이 있다. 본 연구에서는 영상인식기반의 선박 의약품 종합 관리 시스템을 개발하여 의약품 관리를 자동화하고 의료관리자의 업무 효율성을 증가시키고자 한다. 시스템은 의약품 용기·포장지를 촬영한 영상으로부터 글자를 인식하는 OCR(Optical Character Recognition) 기술을 활용한 모듈, 바코드를 인식모듈, 사용자가 검색할 수 있는 모듈로 구성되어있으며 선박 의약품을 데이터베이스화하여 전산으로 관리할 수 있다. 또한 시스템을 통하여 의약품 재고 관리를 하거나 의약품의 사용법을 확인할 수 있다.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.968-976
• /
• 1999

Currently, in the most mail automatic processing centers, after facing and canceling, envelope mail is passed through an Optical Character Recognition/Barcode Sorter(OCR/BS) to read the address and 3 of 5 fluorescent(luminescent) barcode is applied. Normally, 30%∼35% of this mail is rejected. The usual reasons for read failure are poor printing quality of address and barcode, script printing and failure to locate the address. This paper describes a verification system of the postal 3 of 5 customer barcode for solving this problem. The certification system of the 3 of 5 customer barcode consists of barcode verification system and postal address database. The purpose of certification system of the customer barcode verifies the postal 3 of 5 customer barcode and tests matching of mail piece postal address, and retrieves postal code.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.3
• /
• pp.229-236
• /
• 2011

In this paper we present light weighted English-to-Korean and Korean-to-English mobile translators on smart phones. For natural translation and higher translation quality, translation engines are hybridized with Translation Memory (TM) and Rule-based translation engine. In order to maximize the usability of the system, we combined an Optical Character Recognition (OCR) engine and Text-to-Speech (TTS) engine as a Front-End and Back-end of the mobile translators. With the BLEU and NIST evaluation metrics, the experimental results show our E-K and K-E mobile translation equality reach 72.4% and 77.7% of Google translators, respectively. This shows the quality of our mobile translators almost reaches the that of server-based machine translation to show its commercial usefulness.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.610-616
• /
• 2023

In this paper, we implement an unmanned delivery robot system with Robot Operating System(ROS)-based mobile manipulator, and introduce the technologies employed for the system implementation. The robot consists of a mobile robot capable of autonomous navigation inside the building using an elevator and a Selective Compliance Assembly Robot Arm(SCARA)-Type manipulator equipped with a vacuum pump. The robot can determines the position and orientation for picking up a package through image segmentation and corner detection using the camera on the manipulator. The proposed system has a user interface implemented to check the delivery status and determine the real-time location of the robot through a web server linked to the application and ROS, and recognizes the shipment and address at the delivery station through You Only Look Once(YOLO) and Optical Character Recognition(OCR). The effectiveness of the system is validated through delivery experiments conducted within a 4-story building.

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.65-77
• /
• 2004

This paper presents a priori and the local font classification method. The font classification uses ascenders, descenders, and serifs extracted from a word image. The gradient features of those sub-images are extracted, and used as an input to a neural network classifier to produce font classification results. The font classification determines 2 font styles (upright or slant), 3 font groups (serif sans-serif or typewriter), and 7-font names (Postscript fonts such as Avant Garde, Helvetica, Bookman, New Century Schoolbook, Palatine, Times, and Courier). The proposed a priori and local font classification method allows an OCR system consisting of various font-specific character segmentation tools and various mono-font character recognizers. Experiments have shown font classification accuracies reach high performance levels of about 95.4 percent even with severely touching characters. The technique developed for tile selected 7 fonts in this paper can be applied to any other fonts.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.412-416
• /
• 2007

본 논문에서는 OCR(Optical Character Recognition)의 정확도를 위해 인쇄체 한글 문서 영상에 대한 자동 평가방법을 제안한다. 자동 평가방법은 문서가 스캔된 상태에 따라 낮은 해상도, 영상 자체의 기울어짐, 많은 잡음 등을 판단하여 인식하지 않고도 인식률을 추측할 수 있다. 평가방법은 영상 자체의 밝기, 기울기, 영역의 특징, 문자의 상태 등을 특징 항목으로 만들어 점수를 산출한다. 각 항목의 점수는 가장 높은 인식률을 가지는 영상의 특징 값을 기준으로 삼는다. 각각의 특징에 대해 점수가 산출되면 인식률에 높은 비중을 차지하는 특징에 높은 가중치를 적용하여 최종 점수를 산출한다. 영상 평가방법을 통해 높은 점수를 얻은 영상은 상용 인식기를 통해 인식한 결과 높은 인식률을 나타냈고, 평가방법에서 낮은 점수를 받은 영상은 상대적으로 낮은 인식률을 나타냈다. 본 논문에서 제안하는 문서영상을 위한 자동 평가방법은 인식기를 사용하지 않고 영상의 품질을 측정하기 때문에 빠른 시간에 인식률을 추측할 수 있고, 낮은 인식률을 보일 수 있는 영상에 대해서는 항목별 점수를 피드백으로 사용할 수 있어 인식하기전 문서 영상의 전처리에 과정에 도움을 줄 수 있다.

• Journal of Information Management
• /
• v.26 no.1
• /
• pp.16-51
• /
• 1995

Information management area faced new challenge arised from the developments of the computer and the information network, and the advent of information super highway. With deep perception of importance of the information, developments of information technologies, and change of the users' environment, we came to envision the digital library. This paper intends to describe the concept and function of the digital library, and to examine some of information technologies such as CD-ROM, OCR technology and image scanning, hypertext, hypermedia and multimedia. And it also considers the strategies for electronic information services and the applicability of the current information technology for digitalization by case studies of the existing database systems.