• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.632-635
• /
• 1988

이 논문에서는 필기체 한글 인식에 있어서 입력된 기본자소를 window를 이용한 윤곽선 추적과 삼각분할에 의한 이분점 추출에 의해 각 기본자소가 갖고있는 특징성분을 찾아내고 그 특징성분에 의해 문자의 골격을 추출하여 인식하는 방법을 제안하였다. 윤곽선 추적시 window를 이용함으로 간단한 잡음제거와 추적속도를 증가 시켰으며 삼각분할에 의한 이분점 추출방법을 사용함으로 단순한 윤곽선 추적에 의해 특징성분을 추출하는 방법보다 문자의 특징성분을 정확하게 추출할 수 있다는 장점을 갖는다.

• Journal of the Korea Society of Computer and Information
• /
• v.9 no.3
• /
• pp.121-125
• /
• 2004

In the most of recognizing systems of hand-written numbers. extraction of feature shape by using character elements shapes and a method of morphological analysis by using then extraction of feature shapes were usually used. In this paper, however, peculiar chain-code is used, and differential code which gets minimal value by differentiating the chain-code which is generated by the peculiar chain-code is made. We found this differential code is very successful in discriminating hand-written numbers according to the result of applying to most of the hand-written numbers. Testing recognition of hand-written numbers by HMM network. From the results, we can recognize of 96.1 percentage hand-written numbers but can not recognize extremely distorted hand-written numbers.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.143-146
• /
• 2017

심층학습 모델 중 LSTM-CRF는 개체명 인식, 품사 태깅과 같은 sequence labeling에서 우수한 성능을 보이고 있다. 한국어 개체명 인식에 대해서도 LSTM-CRF 모델을 기본 골격으로 단어, 형태소, 자모음, 품사, 기구축 사전 정보 등 다양한 정보와 외부 자원을 활용하여 성능을 높이는 연구가 진행되고 있다. 그러나 이런 방법은 언어 자원과 성능이 좋은 자연어 처리 모듈(형태소 세그먼트, 품사 태거 등)이 없으면 사용할 수 없다. 본 논문에서는 LSTM-CRF와 최소한의 언어 자원을 사용하여 다국어에 대한 개체명 인식에 대한 성능을 평가한다. LSTM-CRF의 입력은 문자 기반의 n-gram 표상으로, 성능 평가에는 unigram 표상과 bigram 표상을 사용했다. 한국어, 일본어, 중국어에 대해 개체명 인식 성능 평가를 한 결과 한국어의 경우 bigram을 사용했을 때 78.54%의 성능을, 일본어와 중국어는 unigram을 사용했을 때 각 63.2%, 26.65%의 성능을 보였다.

• Journal of Korea Multimedia Society
• /
• v.2 no.3
• /
• pp.297-307
• /
• 1999

A character recognition system, where a large amount of character images arrive continuously in real time, must preprocess character images very quickly. Moreover, information loss due to image trans-formations such as geometric normalization and thinning needs to be minimized especially when character images are small and noisy. Therefore, we suggest a prompt and effective feature extraction method without transforming original images. For this, boundary pixels are defined in terms of the degree in classification, and those boundary pixels are considered selectively in extracting features. The proposed method is tested by a handwritten character recognition and a car plate number recognition. The experiments show that the proposed method is effective in recognition compared to conventional methods. And an overall reduction of execution time is achieved by completing all the required processing by a single image scan.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.143-146
• /
• 2017

심층학습 모델 중 LSTM-CRF는 개체명 인식, 품사 태깅과 같은 sequence labeling에서 우수한 성능을 보이고 있다. 한국어 개체명 인식에 대해서도 LSTM-CRF 모델을 기본 골격으로 단어, 형태소, 자모음, 품사, 기구축 사전 정보 등 다양한 정보와 외부 자원을 활용하여 성능을 높이는 연구가 진행되고 있다. 그러나 이런 방법은 언어 자원과 성능이 좋은 자연어 처리 모듈(형태소 세그먼트, 품사 태거 등)이 없으면 사용할 수 없다. 본 논문에서는 LSTM-CRF와 최소한의 언어 자원을 사용하여 다국어에 대한 개체명 인식에 대한 성능을 평가한다. LSTM-CRF의 입력은 문자 기반의 n-gram 표상으로, 성능 평가에는 unigram 표상과 bigram 표상을 사용했다. 한국어, 일본어, 중국어에 대해 개체명 인식 성능 평가를 한 결과 한국어의 경우 bigram을 사용했을 때 78.54%의 성능을, 일본어와 중국어는 unigram을 사용했을 때 각 63.2%, 26.65%의 성능을 보였다.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.14 no.5
• /
• pp.15-21
• /
• 1977

The syntactic pattern recognition system of Korean characters is composed of three main functional parts; Preprocessing, Graph-representation, and Segmentation. In preprocessing routine, the input pattern has been thinned using the Hilditch's thinning algorithm. The graph-representation is the detection of a number of nodes over the input pattern and codification of branches between nodes by 8 directional components. Next, segmentation routine which has been implemented by top down nondeterministic parsing under the control of tree grammar identifies parts of the graph-represented Pattern as basic components of Korean characters. The authors have made sure that this system is effective for recognizing Korean characters through the recognition simulations by digital computer.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.11
• /
• pp.1175-1184
• /
• 1992

A new classification method and recognition algorithms for printed Korean and Chinese character is studied for Korean text which contains both Korean and Chinese characters. The proposed method utilizes structural features of the vertical and horizontal vowel in Korean character. Korean characters are classified into 6 groups. Vowel and consonant are separated by means of different vowel extraction methods applied to each group. Time consuming thinning process is excluded. A modified crossing distance feature is measured to recognize extracted consonant. For Chinese character, an average of stroke crossing number is calculated on every characters, which allows the characters to be classified into several groups. A recognition process is then followed in terms of the stroke crossing number and the black dot rate of character. Classification between Korean and Chinese character was at the rate of 90.5%, and classification rate of Ming-style 2512 Korean characters was 90.0%. The recognition algorithm was applied on 1278 characters. The recognition rate was 92.2%. The densest class after classification of 4585 Chinese characters was found to contain only 124 characters, only 1/40 of total numbers. The recognition rate was 89.2%.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.6 no.4
• /
• pp.8-19
• /
• 1969

This paper attempts to analyize struture of the Letters for the Purpose of makin grecognition of Han-Gelul printed and described the method of recogniton and design of the optimum system. For the reason of the Consistency of Han-Geul (korean letters) combined with Consonants and vouels, the number of the words used in the daily living is about 2,000words. for this reason the composition of the recognition system is complicated, and therfore, this paper is pursued to recearch to handle the separate way ineach form of Letter between consonant and vouel. and the further description of this paper also indicates us the many parts of savings of elements when the character is extracted as logic system in letter composition.

• 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.

• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.900-904
• /
• 1991

In this paper, our study for the recognition of Hand-written Korean characters, Arabic numbers and alphabets by neural netwoks. This System extracts feature of character by using the MESH feature point of handwritten character, Arabic numbers and alphabets. To reduce the input image data, features are extracted from each input images. A MLP(multi-layer perceptron) with one hidden layer was trained with a modified BEP(back error propagation) algorithm. This method extracts feature sets of the characters directly from the scanner and can enhance computation speed without using the special preprocesses such as size normalization, smoothing, and thinning.