• 한국정보통신학회논문지
• /
• 제25권4호
• /
• pp.523-529
• /
• 2021

4차산업 혁명 시대를 맞아, 기술의 변화가 다양한 분야에 적용되고 있다. 고지서 분야에서도 자동화, 디지털화, 데이터관리가 되고 있다. 사회에서 유통되는 고지서의 형태는 수만 가지 이상이며, 이를 자동화, 디지털화, 데이터관리를 위해서는 고지서 인식이 필수적이다. 현재 다양한 고지서들을 관리하기 위해서 OCR(Optical Character Recognition) 기술을 활용한다. 이때, 정확도를 높이기 위해, 먼저 고지서 양식을 인식하면, OCR 인식 시 더 높은 인식률을 가질 수 있다. 본 논문에서는 고지서 양식을 구분하기 위해 인덱스로 사용할 수 있는 로고를 객체 인식하였으며, 이때 로고의 크기가 전체 고지서 대비 작으므로 딥러닝 기술 중 FPN(Feature Pyramid Network)을 작은 객체 검출에 활용하였다. 결과적으로, 제안하는 알고리즘을 통해서 자원 낭비를 줄이고, OCR 인식 정확도를 높일 수 있었다.

• 제어로봇시스템학회논문지
• /
• 제17권5호
• /
• pp.479-483
• /
• 2011

The automation of production process is actively expanding for the purpose of the cost reduction and quality assurance. Among these, automatic tracking of the product along the whole process of the production is also important topic. Typically this is done by adopting OCR technology. Conventional OCR technology operates well on the rather good quality of the image like as printed characters on the paper. In industrial application, IDs are marked on the metal surface, and this cause the height difference between background material and character. Illumination systems that guarantee an image with good quality may be a solution, but it is rather difficult to design such an illumination system. This paper proposes an algorithm for the recognition of vehicle's ID characters using edge projection and PCA (Principal Component Analysis). Proposed algorithm robustly operates under illumination change using the same parameters. Experimental results show the feasibility of the proposed algorithm.

• 정보관리학회지
• /
• 제9권1호
• /
• pp.131-164
• /
• 1992

본 연구에서는 광기술을 이용한 보고서 서지정보와 원문정보를 관리할 수 있는 보고서관리시스템을 개발하였다. 시스템을 현재 상업적으로 보급되고 있는 문서용 광화일링시스템과의 비교평가를 통하여 보고서관리에 적합하고, 도서관 업무에 효율화에 직접적으로 기여할 수 있는 구조로 설계되었으며, 디지탈 이미지 처리기술, MARC 표준, 영문 OCR등의 기술이 사용되었다. (키워드 : 디지탈 이미지, 광기술, 전문데이타베이스, 표준화, 기술보고서, MARC, 광학문자인식)

• 해양환경안전학회지
• /
• 제19권3호
• /
• pp.241-247
• /
• 2013

Yellow clay dispersion has been applied to minimize fisheries impact by the red tide Cochlodinium polykrikoides blooms in Korean coasts since 1995. The present preliminary study documents the effect of yellow clay on Korean rockfish, Sebastes schlegelii, in terms of oxygen consumption rate (OCR). The OCR in the low clay suspension (0.05 and 0.23 %, w/w) showed normal level compared to the control. In contrast, the OCR for each one of three replicates in the high clay suspension (1.16 and 5.58 %, w/w) was not returned to the previous level that clay was not treated, indicating that high clay suspension (${\geq}1.16%$, w/w) might give negative effect on Korean rockfish. Overall, this result suggests that field application of clay to control Harmful Algal Blooms (HABs) may not give impact on Korean rockfish once the clay is dispersed in a low concentration (${\leq}0.23%$). In order to understand the changes of OCR in the repeated exposure to clay, it is required to do further studies on the changes of OCR when the fish is exposed to clay repeatedly after recovery in the normal seawater.

• KIEE International Transactions on Power Engineering
• /
• 제2A권3호
• /
• pp.89-94
• /
• 2002

In this paper, a protection system using a Multi-Agent concept for power distribution networks is proposed. Every digital over current relay(OCR) is developed as an agent by adding its own intelligence, self-tuning and communication ability. The main advantage of the Multi-Agent concept is that a group of agents work together to achieve a global goal which is beyond the ability of each individual agent. In order to cope with frequent changes in the network operation condition and faults, an OCR agent, suggested in this paper, is able to detect a fault or a change in the network and find its optimal parameters for protection in an autonomous manner considering information of the whole network obtained by communication between other agents. Through this kind of coordination and information exchanges, not only a local but also a global protective scheme is completed. Simulations in a simple distribution network show the effectiveness of the suggested protection system.

• 한국정보처리학회논문지
• /
• 제6권7호
• /
• pp.1713-1723
• /
• 1999

문자 인식 기술은 인쇄도니 형태로 존재하는 수많은 정보를 데이터베이스화 할 수 있는 가장 유용한 대안이다. 본 논문에서는 문자 인식 기술을 사용한 데이터베이스 구축의 타당성을 조사하기 위하여, 문자인식기를 사용한 데이터베이스를 시범적으로 구축하였다. 우선 데이터베이스를 구축할 때 문자 인식기의 선택 시 고려하여야 할 사항들을 살펴보고, 이를 기준으로 4가지의 상용 문자 인식기에 대한 인식 실험을 거친 후 그 중 인식 성능이 가장 좋은 것을 선택하였다. 대상 문서로는 다양한 인쇄 품질 및 특성을 갖는 실제 논문집의 초록을 대상으로 삼았으며, 대량 데이터에 대한 인식률 계산을 위해 수작업된 데이터베이스가 있는 KT 테스트 컬렉션[1]을 선택하였다. 실험은 실제 대용량 데이터베이스 구축과 유사한 환경을 만들기 위해, 문서별 학습이나 기울기 보정 등의 사전 작업을 생략하였다. 실험 결과 970편의 논문 요약문에 대해 평균 문자 인식률 90.5%를 보여, 한글 문자 인식 기술이 아직 데이터베이스 구축에 활용되기에는 이르다는 것을 보였다. 문자 인식에 의한 인식 오류에서는 수작업 한 문서에서 발견되는 오류와는 상이한 유형이 많이 발견된다. 본 논문에서는 추후의 연구를 위하여 문자 인식 텍스트에서 나타나는 오류의 유형을 분류하였다.

• Journal of Information Processing Systems
• /
• 제19권3호
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• 정보관리연구
• /
• 제26권1호
• /
• pp.16-51
• /
• 1995

정보관리 분야에서는 컴퓨터와 정보 네트워크의 발달, 그리고 초고속 정보통신망 구축과 같은 환경변화로 인하여 새로운 시대를 맞이하고 있다. 이러한 변화의 시대에 정보의 중요성과 새로운 정보기술의 발달, 정보이용자들의 주변환경 변화를 인식하게 됨에 따라 디지털 도서관(digital library)을 구상하게 되었다. 본고에서는 새롭게 등장한 디지털 도서관의 개념과 기능을 알아보고, CD-ROM, OCR 기법과 이미지 스캐닝, hypertext, hypermedia, multimedia와 같은 정보기술에 대해서 살펴보았다. 또한 이러한 기술을 응용한 시스템 사례를 살펴봄으로써 정보관리 분야에서 새로운 전자정보 서비스를 위한 전략과 정보의 디지털 화를 위한 응용가능성을 살펴보고자 한다.

• 반도체디스플레이기술학회지
• /
• 제20권3호
• /
• pp.6-10
• /
• 2021

Recognition of characters printed or marked on the PCB components from images captured using cameras is an important task in PCB components inspection systems. Previous optical character recognition (OCR) of PCB components typically consists of two stages: character segmentation and classification of each segmented character. However, character segmentation often fails due to corrupted characters, low image contrast, etc. Thus, OCR without character segmentation is desirable and increasingly used via deep neural networks. Typical implementation based on deep neural nets without character segmentation includes convolutional neural network followed by recurrent neural network (RNN). However, one disadvantage of this approach is slow execution due to RNN layers. LPRNet is a segmentation-free character recognition network with excellent accuracy proved in license plate recognition. LPRNet uses a wide convolution instead of RNN, thus enabling fast inference. In this paper, LPRNet was adapted for recognizing characters printed on PCB components with fast execution and high accuracy. Initial training with synthetic images followed by fine-tuning on real text images yielded accurate recognition. This net can be further optimized on Intel CPU using OpenVINO tool kit. The optimized version of the network can be run in real-time faster than even GPU.

• International Journal of Contents
• /
• 제13권4호
• /
• pp.70-79
• /
• 2017

Images are an important element in patents and many experts use images to analyze a patent or to check differences between patents. However, there is little research on image analysis for patents partly because image processing is an advanced technology and typically patent images consist of visual parts as well as of text and numbers. This study suggests two methods for using image processing; the Scale Invariant Feature Transform(SIFT) algorithm and Optical Character Recognition(OCR). The first method which works with SIFT uses image feature points. Through feature matching, it can be applied to calculate the similarity between documents containing these images. And in the second method, OCR is used to extract text from the images. By using numbers which are extracted from an image, it is possible to extract the corresponding related text within the text passages. Subsequently, document similarity can be calculated based on the extracted text. Through comparing the suggested methods and an existing method based only on text for calculating the similarity, the feasibility is achieved. Additionally, the correlation between both the similarity measures is low which shows that they capture different aspects of the patent content.