• International Journal of Advanced Culture Technology
• /
• 제6권2호
• /
• pp.123-128
• /
• 2018

Learning data is composed of 100 characters with 10 different fonts, and test data is composed of 10 characters with a new font that is not used for the learning data. In order to consider the variety of learning data with several different fonts, 10 learning masks are constructed by accumulating pixel values of same characters with 10 different fonts. This process eliminates minute difference of characters with different fonts. After finding maximum values of learning masks, test data is expanded by multiplying these maximum values to the test data. The algorithm calculates sum of differences of two corresponding pixel values of the expanded test data and the learning masks. The learning mask with the smallest value among these 10 calculated sums is selected as the result of the recognition process for the test data. The proposed algorithm can recognize various types of fonts, and the learning data can be modified easily by adding a new font. Also, the recognition process is easy to understand, and the algorithm makes satisfactory results for character recognition.

• 한국통신학회논문지
• /
• 제15권6호
• /
• pp.455-466
• /
• 1990

영문자 및 기호를 인식할 수 있는 프로그램을 개발하였으며, 이 소프트웨어로 전처리 수행한 결과 속도의 한계성이 있었다. 이 속도의 한계를 극복하고자 신경회로망 알고리즘을 이용해 전처리 과정용 집적회로 칩을 설계하였다. 설계된 칩은 잡음제거, 선형화, 세선화 및 특징점 추출을 위한 것이다. 이 칩들은 단층 구조 퍼셉트론 신경회로 모델에 따라 CMOS 이중 금속 2um 설계 규칙에 의하 설계되었다.

• 한국멀티미디어학회논문지
• /
• 제2권3호
• /
• pp.297-307
• /
• 1999

다량의 문자가 온라인으로 실시간 입력되는 문자인식시스템에서는 영상의 전처리가 매우 신속하게 이루어 져야 한다. 또한 크기가 작거나 잡음을 포함하는 문자 영상에 대한 기하학적 정규화나 세선화 등의 영상 변환은 원영상의 정보 유실이나 왜곡을 유발하므로 최소화되어야 한다. 이에 따라 본 연구는 원영상을 변환하지 않은 상태에서 신속하게 인식에 효과적인 특정을 구하고자 하였다. 이를 위해 인식의 관점에서 의미를 가지는 윤곽화소를 정의하고 다양한 영상의 변화를 수용하는 효과적인 특징을 윤곽화소로부터 구하였다. 필기체 자모음과 자동차 번호판 숫자 인식 실험 결과, 제안된 방법이 기존의 방법보다 인식에 보다 효과적이었으며 한번의 영상 주사로 전처리를 완료하므로 소요 시간을 크게 줄일 수 있었다.

• 한국컴퓨터정보학회논문지
• /
• 제22권3호
• /
• pp.97-105
• /
• 2017

This study is the realization study recognizing the Korean gothic printing letter. This study defined the new grapheme by using the connection ingredient and had the graphemes recognized by means of the feature dots of the isolated dot, end dot, 2-line gathering dots, more than 3 lines gathering dots, and classified the characters by means of the arrangement information of the graphemes and the layers that the graphemes form within the characters, and made the character database for the recognition by using them. The layers and the arrangement information of the graphemes consisting in the characters were presumed by using the weight center position information of the graphemes extracted from the characters to recognize and the information of the graphemes obtained by vertically exploring from the weight center of each grapheme, and it recognized the characters by judging and comparing the character groups of the database by means of the information which was secured this way. 350 characters were used for the character recognition test and about 97% recognition result was obtained by recognizing 338 characters.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2004년도 정기총회 및 학술대회
• /
• pp.237-240
• /
• 2004

This paper describes a character retrieval system for TV programs and a set of novel algorithms for detecting and recognizing faces for the system. Our character retrieval system consists of two main components: Face Register and Face Recognizer. The Face Register detects faces in video frames and then guides users to register the detected faces of interest into the database. The Face Recognizer displays the appearance interval of each character on the timeline interface and the list of scenes with the names of characters that appear on each scene. These two components also provide a function to modify incorrect results. which is helpful to provide accurate character retrieval services. In the proposed face detection and recognition algorithms. we reduce the computation time without sacrificing the recognition accuracy by using the DCT/LDA method for face feature extraction. We also develop the character retrieval system in the form of plug-in. By plugging in our system to a cataloguing system. the metadata about the characters in a video can be automatically generated. Through this system, we can easily realize sophisticated on-demand video services which provide the search of scenes of a specific TV star.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.380-382
• /
• 2021

2020년에 경찰청에서 조사한 자료에 따르면 38,496건 중에 미해결 사건이 161건으로, 미해결 원인 중 가장 높은 성인실종자의 경우는 대부분 단순 가출로 평가된다. CCTV를 통해 영상을 통해 찾는 경우에도 수많은 사람이 지나가는 상황에 인물들의 얼굴을 일일이 확인하고 진술의 특징들로만 인물을 찾아내야 하기 때문에 긴 시간이 걸리고 정확도가 낮아 수사에 많은 시간이 소요되는 것이 확인되었다. 본 논문은 MTCNN을 활용하여 CCTV 속 인물 추출에 대한 연구를 진행하였다. MTCNN으로 학습된 얼굴들과 입고 있는 옷의 특징을 동시에 분석을 시작하여 겹쳐지는 경우의 인물들만 추출하여 관계자에게 확인이 가능하도록 한다. 향후 실종자의 특징들을 좁혀 정확도를 높이기 위해 더 다양한 특징 검출 학습을 목표로 한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1183-1186
• /
• 2004

In the steel production line, the molten metal of a furnace is transformed into billet and then moves to the heating furnace of the hot rolling mill. This paper describes about the realtime billet characters recognition system in the steel production line. Normally, the billets are mixed at yard so that their identifications are very difficult and very important processing. The character recognition algorithm used in this paper is base on the subspace method by K-L transformation. With this method, we need no special feature extraction steps, which are usually error prone. So the gray character images are directly used as input vectors of the classifier. To train the classifier, we have extracted eigen vectors of each character used in the billet numbers, which consists of 10 arabia numbers and 26 alphabet aharacters, which are gathered from billet images of the production line. We have developed billet characters recognition system using this algorithm and tested this system in the steel production line during the 8-days. The recognition rate of our system in the field test has turned out to be 94.1% (98.6% if the corrupted characters are excluded). In the results, we confirmed that our recognition system has a good performance in the poor environments and ill-conditioned marking system like as steel production plant.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1275-1277
• /
• 2003

This paper presents a geological remote sensing information extraction system, the aim of which is to provide practical models and powerful tools to extract geological information from remote sensing images for geological exploration applications. After reviewing and analyzing the existing methods for geological information extraction, we developed more than ten models to enhance and extract geological information, such as alteration information, linear features and special lithological characters. The system is developed based on Erdas Imagine using its programming language. It has been successfully used in the 'reat Investigation of Land and Natural Resources of China' program.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1442-1444
• /
• 2003

This paper presents a geological remote sensing information extraction system, the aim of which is to provide practical models and powerful tools to extract geological information from remote sensing images for geological exploration applications. After reviewing and analyzing the existing methods for geological information extraction, we developed more than ten models to enhance and extract geological information, such as alteration information, linear features and special lithological characters. The system is developed based on Erdas Imagine using its programming language. It has been successfully used in the ‘Great Investigation of Land and Natural Resources of China’ program.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1999년도 가을 학술발표논문집 Vol.26 No.2 (2)
• /
• pp.315-317
• /
• 1999

미세한 차이를 고감도 식별하는 카오스 이론의 프랙탈 차원과 스트레인즈 어트랙터를 생성하는 수정된 에농 함수를 이용하여, 한글 2,350자에 대한 시계열 데이터의 혼도도를 분석하기 위해, 각각의 문자 0트랙터를 구성한 후, 프랙탈 차원을 나타내는 Box-counting Dimension 및 Natural Measure, Information Bit, Information Dimension 등을 구하여 문자 특징을 추출하는 새로운 알고리즘을 제시하였다. 실험결과 한글 2,350자에 대하여 99.23%의 분류율을 나타내어 제안된 방법의 유효성을 보였다.