• 정보처리학회논문지B
• /
• 제17B권2호
• /
• pp.125-138
• /
• 2010

본 연구는 공공기관이 소장한 이미지데이터의 검색 및 열람 등의 활용성을 높이기 위한 전문검색서비스 구현 시 필수적인 문서인식시스템의 고도화를 목표로 한다. 주요한 연구방향은 공공기관이 소장하고 있는 데이터를 사전에 분석하여 문서이미지 전처리 및 문서구조분석 기술을 개발하고, 문서인식 과정에서 활용하기 위한 이미지내용DB, 문자모델DB, 용어DB로 구성되는 특화된 지식베이스를 구축하는 것이다. 또한, 지식베이스 관리도구를 개발하여 향후 다양한 형태의 문서이미지로의 확장을 가능하게 한다. 최근 본 연구는 국가기록원에서 소장하고 있는 이미지데이터에 적합한 문서구조분석 라이브러리와 특화된 지식베이스를 결합한 문서인식 프로토타입 시스템 개발을 완료했다. 향후 본 연구의 결과는 방대한 소장자료의 검색 및 활용을 극대화할 전문검색시스템 연계를 위한 성능평가 및 테스트베드 구축에 활용될 것이다.

• 한국ITS학회 논문지
• /
• 제18권6호
• /
• pp.241-250
• /
• 2019

도로표지는 도로 이용자를 위한 시설물로서 관리 및 유지보수의 편의성 증진을 위해 국토교통부에서는 관리시스템을 구축하여 운영 중에 있다. 향후 자율주행 시대에 도로표지의 역할은 감소하겠지만 그 필요성은 지속되고 있다. 이에 도로표지에 표기된 안내지명의 정확한 기계적 판독을 위해 도로표지 자동인식 장비를 개발하여 영상 기반의 문자 인식 기술을 적용하고 있지만 불규칙적인 규격과 수작업 제조, 조도, 빛반사, 강우 등 외부환경에 의해 오인식되는 경우가 다수 발생하고 있다. 본 연구에서는 영상 분석 등으로 극복할 수 없는 오인식 결과를 개선하기 위해 위치기반의 안내지명 후보를 도출하여 기준으로 하고, 오인식된 지명의 음소 분리를 통한 레벤슈타인 문자 유사도 검증 방법을 이용해 도로표지 안내지명 자동인식율을 개선하고자 하였다.

• 한국ITS학회 논문지
• /
• 제13권2호
• /
• pp.27-33
• /
• 2014

This paper proposes a gradation image processing method for the development of a Road Sign Recognition Platform (RReP), which aims to facilitate the rapid and accurate management and surveying of approximately 160,000 road signs installed along the highways, national roadways, and local roads in the cities, districts (gun), and provinces (do) of Korea. RReP is based on GPS(Global Positioning System), IMU(Inertial Measurement Unit), INS(Inertial Navigation System), DMI(Distance Measurement Instrument), and lasers, and uses an imagery information collection/classification module to allow the automatic recognition of signs, the collection of shapes, pole locations, and sign-type data, and the creation of road sign registers, by extracting basic data related to the shape and sign content, and automated database design. Image division and merging, which were applied in this study, produce superior results compared with local binarization method in terms of speed. At the results, larger texts area were found in images, the accuracy of text recognition was improved when images had been gradated. Multi-threshold values of natural scene images are used to improve the extraction rate of texts and figures based on pattern recognition.

• Journal of Information Processing Systems
• /
• 제8권4호
• /
• pp.575-588
• /
• 2012

Exploiting unlabeled text data with a relatively small labeled corpus has been an active and challenging research topic in text mining, due to the recent growth of the amount of biomedical literature. Biomedical named-entity recognition is an essential prerequisite task before effective text mining of biomedical literature can begin. This paper proposes an Active Co-Training (ACT) algorithm for biomedical named-entity recognition. ACT is a semi-supervised learning method in which two classifiers based on two different feature sets iteratively learn from informative examples that have been queried from the unlabeled data. We design a new classification problem to measure the informativeness of an example in unlabeled data. In this classification problem, the examples are classified based on a joint view of a feature set to be informative/non-informative to both classifiers. To form the training data for the classification problem, we adopt a query-by-committee method. Therefore, in the ACT, both classifiers are considered to be one committee, which is used on the labeled data to give the informativeness label to each example. The ACT method outperforms the traditional co-training algorithm in terms of f-measure as well as the number of training iterations performed to build a good classification model. The proposed method tends to efficiently exploit a large amount of unlabeled data by selecting a small number of examples having not only useful information but also a comprehensive pattern.

• 한국가정과교육학회지
• /
• 제7권2호
• /
• pp.113-123
• /
• 1995

The purpose of this study is to investigate teachers’ recognition in Food/Nutrition, Textile/Clothing part in Home Economics Text Book of Middle School and to provide the basic data for the improvement of its curriculum. 147 Home Economics teachers in Taegu city and Kyungsangbukdo area responded to the questionnaire. The results are summarized as follows: 1. Most of Home Economics teachers have graduated Dept. of Home Economics Education and have ever taken teacher training. And even those who ever taken teacher training are not satisfied with training curriculum contents. Therefore, the result of this study shows that teacher training curriculum contents should be improved so as to be helpful for the actual teaching and learning. 2. In terms of the suitability of contents of food & nutrition and contents of textiles & clothing to the student’s learning development levels, the degree of suitability is in the order of nutrition & health, nutrition in adolescence, food selection, kinds and functions of nutrients in food & nutrition curriculum, and in the order of suitable clothing, mixture rate of fabrics, purchase of clothing, clothing in adolescence, clothing selection. The contents of making processed foods and usage of sewing machine of the existing text book have turned out not to be appropriate. 3. Most teachers suggest that dietary guideline for health, misconception about food & nutrition selection of ready-made suit suitable clothing for situation & character as well as the contents of the existing text book should be included in the new text book.

• 한국IT서비스학회지
• /
• 제15권1호
• /
• pp.245-253
• /
• 2016

Background in a novel is most important elements with characters and events, and means time, place and situation that characters appeared. Among the background, spatial background can help conveys topic of a novel. So, it may be helpful for choosing a novel that readers want to read. In this paper, we are targeting Korean historical novels. In case of English text, It can be recognize spatial background easily because it use upper and lower case and words used with the spatial information such as Bank, University and City. But, in case Korean text, it is difficult to recognize that spatial background because there is few information about usage of letter. In the previous studies, they use machine learning or dictionaries and rules to recognize about spatial information in text such as news and text messages. In this paper, we build a nation dictionaries that refer to information such as 'Korean history' and 'Google maps.' We Also propose a method for recognizing spatial background based on patterns of postposition in Korean sentences comparing to previous works. We are grasp using of postposition with spatial background because Korean characteristics. And we propose a method based on result of morpheme analyze and frequency in a novel text for raising accuracy about recognizing spatial background. The recognized spatial background can help readers to grasp the atmosphere of a novel and to understand the events and atmosphere through recognition of the spatial background of the scene that characters appeared.

• 대한음성학회지:말소리
• /
• 제43호
• /
• pp.57-72
• /
• 2002

The technology of speech recognition has a wide field of application. The range of such technology is spreading into mobile computing having the large amount of movement for communication equipments at the present time. Particularly, recognition in internet environment is rapidly moving into mobile environment. Because of these environments, users want the faster speed of data transmission and the lighter portable equipment for data access. That is PDA(Personal Digital Assistant). Therefore, we designed a triphone-based text independent vocabulary recognizer for the implementation of speech control in this paper. The text independent vocabulary recognizer is based on the state .joint algorithm with decision trees

• International Journal of Computer Science & Network Security
• /
• 제23권4호
• /
• pp.48-54
• /
• 2023

Nowadays, a blind man finds it very difficult to cross the roads. They should be very vigilant with every step they take. To resolve this problem, Convolutional Neural Networks(CNN) is a best method to analyse the data and automate the model without intervention of human being. In this work, a traffic signal recognition system is designed using CNN for the visually impaired. To provide a safe walking environment, a voice message is given according to light state and timer state at that instance. The developed model consists of two phases, in the first phase the CNN model is trained to classify different images captured from traffic signals. Common Objects in Context (COCO) labelled dataset is used, which includes images of different classes like traffic lights, bicycles, cars etc. The traffic light object will be detected using this labelled dataset with help of object detection model. The CNN model detects the color of the traffic light and timer displayed on the traffic image. In the second phase, from the detected color of the light and timer value a text message is generated and sent to the text-to-speech conversion model to make voice guidance for the blind person. The developed traffic light recognition model recognizes traffic light color and countdown timer displayed on the signal for safe signal crossing. The countdown timer displayed on the signal was not considered in existing models which is very useful. The proposed model has given accurate results in different scenarios when compared to other models.

• 문화기술의 융합
• /
• 제10권1호
• /
• pp.617-623
• /
• 2024

언어와 감정 사이의 복잡한 관계의 특징을 보이며, 우리의 말을 통해 감정을 식별하는 것은 중요한 과제로 인식된다. 이 연구는 음성 및 텍스트 데이터를 모두 포함하는 다중 모드 분류 작업을 통해 음성 언어의 감정을 식별하기 위해 속성 엔지니어링을 사용하여 이러한 과제를 해결하는 것을 목표로 한다. CNN(Convolutional Neural Networks)과 LSTM(Long Short-Term Memory)이라는 두 가지 분류기를 BERT 기반 사전 훈련된 모델과 통합하여 평가하였다. 논문에서 평가는 다양한 실험 설정 전반에 걸쳐 다양한 성능 지표(정확도, F-점수, 정밀도 및 재현율)를 다룬다. 이번 연구 결과는 텍스트와 음성 데이터 모두에서 감정을 정확하게 식별하는 두 모델의 뛰어난 능력을 보인다.

• 전자공학회논문지C
• /
• 제36C권7호
• /
• pp.27-35
• /
• 1999

필기서술의 인식과 관련된 연구는 인식대상 영상이 바르게 분리된 인식단위를 포함한다는 전제로 진행되어 왔다. 그러나 실제적인 필기인식 시스템의 설계에 있어서, 다양한 필기방식으로 인해, 인식단위로의 분리가 선결되어야 할 문제이다. 본 논문에서는 제한없이 쓰여진 필기 문자열로부터 인식의 도움없이 독립된 단어를 분리하는 방법을 제안한다. 구성요소간 물리적인 거리에 의존하는 종래의 방법과 달리, 필기서술 자체로부터 필기자의 띄어쓰기와 관련된 특징들을 적극적으로 추출하고 이를 신경회로망을 사용하여 해석한다. 띄어쓰기와 관련된 정보는 문자 분리과정을 통해 분리된 문자 세그먼트의 높이와 세그먼트 중심선 사이의 간격들을 정규화하여 구한다. 연결요소간의 거리에 기반한 방법들과의 비교실험을 통해 제한한 방법의 유용성을 입증하였다.