• Journal of KIISE:Software and Applications
• /
• v.26 no.5
• /
• pp.647-656
• /
• 1999

본 논문에서는 오프라인 무제약 필기 한글 단어를 인식하기 위한 시스템을 제안한다. 제안된 단어 인식 시스템은 크게 다석가지 모듈-문자 분리,조합행렬생성, 특징 추출, 문자인식, 사전 후처리 -로 구성되어 있다. 문자 분리 모듈은 입력된 단어 영상을 하나의 문자보다 더 작은 이미지 조각으로 과다 분리하며 , 조합 행렬 생성모듈에서는 동적 프로그래밍 기법을 이용하여 분리된 이미지 조각들로부터 사전상의 모든 단어들과 대응되는 가능한 모든 조합을 생성한다. 문자인식모듈은 각 그룹에 대하여 일괄적으로 얻어진 특징과 유니그램을 이용하여 문자인식을 수행한다. 마지막으로 사전 후처리 모듈에서는 각 그룹에 대한 문자인식 결과와 단어 사전을 사용하여 입력단어에 대한 최종 인식 결과를 도출한다. 본 문에서 제안한 방법은 문자 분리, 문자 인식 및 후처리를 상호 보완적으로 결합함으로써 한글이 포함된 무제약 필기 문자열을 효과적으로 인식할 수 있다. 제안된 시스템의 성능을 평가하기 위하여 실제 우편 봉투 상에 쓰여진 필기 한글 단어 200개를 대상으로 실험을 하였다. 실험 결과 200개의 단어중 172개의 단어를 정인식하여 86%의 정확도를 얻을 수 있었으며 나머지 28개의 오인식된 단어들을 분석한 결과 대부분의 오류는 문자 인식기의 낮은 신뢰도 때문임을 알 수 있었다. 또한, 하나의 단어를 인식하기 위하여 약 2초가 소요되었다.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.7 no.3
• /
• pp.5-11
• /
• 1970

Some of the coding method have been discussed by extracting characteristics from vowels and consonants of Korean characters. given letters were sampled through 3$\times$5 mesh and also constituted first matrix system which taken subpatterns of vertical Conponent as variables and then, characteristics of the letters are extracted from the second matrix system expresses by common characteristics which are combined-with first one. Single coding was obtained by scanning the characteristic pattern. a good agree between theoretical values and their measurements and the reproducing of all vowels and consonants of Korean chasacters about coding were certified on the display designed.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.151-154
• /
• 2000

차량 번호판 영상을 안정적으로 추출하여 인식하는 방법에는 여러 가지 땅법들이 제시되어 왔다. 기존의 연구들은 번호판 영역 추출에는 높은 성공률을 보이고 있으나 상대적으로 문자 인식의 성공률이 그에 미치지 못해서 전체적인 인식 성공률에 저하를 가져오는 경우가 대부분 이었다. 따라서 본 연구에서는 칼라 정보를 이용하여 입력 영상의 밝기 보정과 번호판 영역을 추출하고 N4M (Normalized 4 - Mash)을 적용하여 문자인식 처리 시간을 단축시키고 인식글을 향상시킬 수 있었다.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.7
• /
• pp.901-914
• /
• 2002

In this paper, We propose an efficient automatic caption detection and location method, caption recognition using FE-MCBP(Feature Extraction based Multichained BackPropagation) neural network for content based retrieval of video. Frames are selected at fixed time interval from video and key frames are selected by gray scale histogram method. for each key frames, segmentation is performed and caption lines are detected using line scan method. lastly each characters are separated. This research improves speed and efficiency by color segmentation using local maximum analysis method before line scanning. Caption detection is a first stage of multimedia database organization and detected captions are used as input of text recognition system. Recognized captions can be searched by content based retrieval method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.7
• /
• pp.618-627
• /
• 1990

In this paper a new algorithm for separation of contacting subpattern and connective feature extraction of strokes is proposed. This algorithm is able to classification of the type of contacting parts, connective feature extreaction of strokes, separate the phoneme of contacting parts between strokes, classify the character types by feature classification of connecting parts and analysis of connecting attribute. Also, shape normalize into formal patterns and decide on the input pattern from position value of bending feature of this normalized shape and make an recognition experiment by neural network using BEP learining algorithm. This algorithm represents the good achievement ratio by separation of phoneme, classification of character type, connective feature extraction of stroke and recognition experiment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.11
• /
• pp.2133-2146
• /
• 1994

In this paper, we present a method for dynamic Jaso segmentation and Hangeul recognition using neural network. It uses the feature vector which is extracted from the mesh depending on the segmentation result. At first, each character is converted to 256 dimension feature vector by four direction contributivity and $8\times8$ mesh. And then, the character is classified into 6 class by neural network and is segmented into Jaso using the classification result the statistic vowel location information and the structural information. After Jaso segmentation, Hanguel recognition using neural network is performed. We experiment on four font of which three fonts are used for training the neural net and the rest is used of testing. Each font has the 2350 characters which are comprised in KS C 5601. The overall recognition rates for the training data and the testing data are 97,4% and 94&% respectively. This result shows the effectivness of proposed method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.3 no.4
• /
• pp.245-250
• /
• 2002

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, Palatino, Times, or 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.

• Korean Journal of Cognitive Science
• /
• v.9 no.1
• /
• pp.1-11
• /
• 1998

In this paper, the features which are thought to be used by humans based on the psychological experiment of human information processing are applied to character recognition problem. Man will deal with a little large area information as well as pixel by pixel information. Therefore we define the feature that represents a little wide region I information called region feature, and combine the features derived from region feature and pixel by pixel features that have been used by now. The features we used are the result of region feature based preanalysis, mesh with region attributes, cross distance difference and gradient. The training and test data in the experiment are handwritten Korean alphabets, digits and English alphabets, which are trained on neural network using back propagation algorithm and recognition results are 90.27-93.25%, 98.00% and 79.73-85.75%, respectively Experimental results show that the feature we are suggesting in this paper is 1-2% better than UDLRH feature similar in attribute to region feature, and the tendency of misrecognition is more easily acceptable by humans.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.20-27
• /
• 2004

We propose the character recognition system for Gerber files. The Gerber file is the vector-formatted drawing file for PCB manufacturing, which includes various symbols, figures and characters. Also, the characters are written in horizontal, vertical, and reverse-vortical directions. In this paper, we newly propose the Gerber-character recognition system to recognize all of component names located in PCB. To improve the performance, we develop the multiple recognizers by neural networks and the verifier considering the structural features. The developed system has been installed to the auto-programming software for PCB assembly and inspection machines.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.61-71
• /
• 2009

Vehicle license plate is the only way to check the registrated information of a vehicle. Many works have been devoted to the vision system of recognizing the license plate, which has been widely used to control an illegal parking. However, it is difficult to correctly segment characters on the license plate since an illumination is affected by a weather change and a neighboring obstacles. This paper proposes a robust method of segmenting the character of the license plate on irregular illumination condition. The proposed method enhance the contrast of license plate images using the Chi-Square probability density function. For segmenting characters on the license plate, binary images with the high quality are gained by applying the adaptive threshold. Preprocessing and labeling algorithm are used to eliminate noises existing during the whole segmentation process. Finally, profiling method is applied to segment characters on license plate from binary images.