• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제20권10호
• /
• pp.549-554
• /
• 2014

필기체 낱글자 인식을 위해서 사용되는 데이터는 일반적으로 다수의 사용자들로부터 수집된 자연언어 문장들을 이용하기 때문에 해당 언어의 언어적 특성에 따라서 낱글자의 종류별 개수 차이가 매우 큰 특징이 있다. 일반적인 기계학습 문제에서 학습데이터의 불균형 문제는 성능을 저하시키는 중요한 요인으로 작용하지만, 필기체 인식에서는 데이터 자체의 높은 분산과 비슷한 모양의 낱글자 등이 성능 저하의 주요인이라 생각하기 때문에 이를 크게 고려하지 않고 있다. 본 논문에서는 이러한 데이터의 불균형 문제를 고려하여 필기체 인식기의 성능을 향상시킬 수 있는 과표본화 기반의 앙상블 학습 기법을 제안한다. 제안한 방법은 데이터의 불균형 문제를 고려하지 않은 방법보다 전체적으로 향상된 성능을 보일 뿐만 아니라 데이터의 개수가 부족한 낱글자들의 분류성능에 있어서도 향상된 결과를 보여준다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.819-822
• /
• 2000

The merit of the stroke extraction algorithm is the ease of the feature abstraction from the skeleton of a character, But, extracting strokes from Korean characters has two major problems that must be dealt with. One is extracting primitive strokes and the other is merging or splitting the strokes using dynamic information of the strokes. In this paper, a method is proposed to extract strokes from an off-line handwritten Korean character. We have developed some stroke segmentation rules based on splitting, merging and directional analysis. Using these techniques, we can extract and trace the strokes in an off-line handwritten Korean character accurately and efficiently.

• 한국인쇄학회지
• /
• 제6권1호
• /
• pp.41-57
• /
• 1988

Recently, it Is required to develop OCR(Optical Character Reader) along with the progress of the information processing system for Hangeul. Characters have to be recognized clearly so that OCR can be applied, Structure analysis method and lump method are used for the recognition of characters, and OCR is now available for the recognition of printed characters and handwritten alphanumeric characters having simple structure by them However, It is known that there should be much more study on the development of handwritten Hangout's OCR. This paper proposed a new method for the handwritten Hangout character recognition. The units of Initial consonant of Hangout are separated and then recognized from the utilization of the position- Information of Hangeul's units from the normalized patterns using the regression line theory. It is carried out for the extraction of the block which exists in the virtual Initial consonant region from the normalized input patterns and the calculation on maximum value (${\beta}$) of likelihood after comparing the features of separated subpattern with the initial consonant dictionary.

• 한국IT서비스학회지
• /
• 제20권6호
• /
• pp.97-105
• /
• 2021

Recently, with the development of IT technology, unmanned systems are being introduced in many industrial fields, and one of the most important factors for introducing unmanned systems in the automobile field is vehicle licence plate recognition(VLPR). The existing VLPR algorithms are configured to use image processing for a specific type of license plate to divide individual areas of a character within the plate to recognize each character. However, as the number of Korean vehicle license plates increases, the law is amended, there are old-fashioned license plates, new license plates, and different types of plates are used for each type of vehicle. Therefore, it is necessary to update the VLPR system every time, which incurs costs. In this paper, we use an object detection algorithm to detect character regardless of the format of the vehicle license plate, and apply a handwritten Hangul recognition(HHR) algorithm to enhance the recognition accuracy of a single Hangul character, which is called a Hangul unit. Since Hangul unit is recognized by combining initial consonant, medial vowel and final consonant, so it is possible to use other Hangul units in addition to the 40 Hangul units used for the Korean vehicle license plate.

• 스마트미디어저널
• /
• 제1권4호
• /
• pp.59-71
• /
• 2012

Since mobile phones are used as common communication devices, their applications are increasingly important to human's life. Using smart-phones camera to collect daily life environment's information is one of targets for many applications such as text recognition, object recognition or context awareness. Studies have been conducted to provide important information through the recognition of texts, which are artificially or naturally included in images and movies acquired from mobile phones. In this study, a character segmentation method that improves character-recognition accuracy in images obtained from mobile phone cameras is proposed. The proposed method first classifies texts in a given image to printed letters and handwritten letters since segmentation approaches for them are different. For printed letters, rough segmentation process is conducted, then the segmented regions are integrated, deleted, and re-segmented. Segmentation for the handwritten letters is performed after skews are corrected and the characters are classified by integrating them. The experimental result shows our method achieves a successful performance for both printed and handwritten letters as 95.9% and 84.7%, respectively.

• International Journal of Ocean System Engineering
• /
• 제2권1호
• /
• pp.57-61
• /
• 2012

In this paper we use the Kohonen neural network based Self Organizing Map (SOM) algorithm for Urdu Character Recognition. Kohenen NN have more efficient in terms of performance as compare to other approaches. Classification is used to recognize hand written Urdu character. The number of possible unknown character is reducing by pre-classification with respect to subset of the total character set. So the proposed algorithm is attempt to group similar character. Members of pre-classified group are further analyzed using a statistical classifier for final recognition. A recognition rate of around 79.9% was achieved for the first choice and more than 98.5% for the top three choices. The result of this paper shows that the proposed Kohonen SOM algorithm yields promising output and feasible with other existing techniques.

• 대한전자공학회논문지
• /
• 제27권11호
• /
• pp.103-110
• /
• 1990

本 論文에서는 퍼지推論을 利用한 온라인 筆記體 한글文字의 認識에 관하여 硏究하였다. 筆記者 마다의 筆體變動으로 인한 애매성을 解決하기 위해, 각 스트로크間의 相對位置情報마다 作成되는 生成 을 퍼지推論에 適用하여 筆記體 한글을 認識하였다. 處理시간을 短縮하기 위하여, 入力文字의 스트로크 數에 따라 미리 分類한 基準文字의 小群을 선택하였고, 이 小群의 文字들과 入力文字와의 거리에 許容限果를 주어 基準文字들을 감소시켜 퍼지推論에 적용하였다. 10人으로부터 수집된 39990字의 筆記體 한글文字에 대하여 實驗한 結果, $99.5{\%}$의 認識과 0.4초/文字의 平均處理 速度를 얻었다.

• 한국콘텐츠학회논문지
• /
• 제5권5호
• /
• pp.152-158
• /
• 2005

문자 패턴에서 추출한 서로 다른 특징 집합을 결합함으로써 문자 인식 시스템의 성능을 향상시킬 수 있다. 이때 결합된 특징 벡터의 차원을 줄이기 위해 특징 선택을 수행해야 한다. 이 논문은 문자 인식 문제에서 특징 결합과 선택을 위한 일반적인 틀을 제시한다. 또한 필기 숫자 인식을 위한 설계와 구현을 제시한다. 이 설계에서는 필기 숫자 패턴에서 DDD 특징 집합과 AGD 특징 집합을 추출하며 특징 선택을 위해 유전 알고리즘을 사용한다. 실험 결과 CENPARMI 필기 숫자 데이터베이스에 대해 0.7%의 정확률 향상을 얻었다.

• 한국산업정보학회논문지
• /
• 제29권3호
• /
• pp.13-22
• /
• 2024

현재 디지털 기기의 확산과 함께 일상에서 손으로 쓰는 글씨의 비중은 점점 줄어들고 있다. 키보드와 터치스크린의 활용도 증가에 따라 한글 필기체의 품질 저하는 어린 학생부터 성인까지 넓은 범위의 한글 문서에서 관찰되고 있다. 그러나 한글 필기체는 여전히 개인적인 고유한 특징을 포함하면서 가독성을 제공하는 많은 문서 작성에 필요하다. 이를 위해 본 논문에서는 손으로 쓴 한글 필기체의 품질을 개선하고, 교정하기 위한 목적의 어플 구현을 목적으로 한다. 제안된 어플은 CRAFT(Character-Region Awareness For Text Detection) 모델을 사용하여 필기체 영역을 검출하고, 딥러닝으로서 VGG-Feature-Extraction 모델을 사용하여 필기체의 특징을 학습한다. 이때 사용자가 작성한 한글 필기체의 음절 단위로 신뢰도를 인식률로 제시하고, 또한, 후보 폰트들중에서 가장 유사한 글자체를 추천하도록 구현한다. 다양한 실험을 통해 제안한 어플은 기존의 상용화된 문자 인식 소프트웨어와 비교할만한 우수한 인식률을 제공함을 확인할 수 있다.

• Journal of Information Processing Systems
• /
• 제13권1호
• /
• pp.174-183
• /
• 2017

In this paper, we propose a novel feature for recognizing handwritten Odia numerals. By using polygonal approximation, each numeral is segmented into segments of equal pixel counts where the centroid of the character is kept as the origin. Three primitive contour features namely, distance (l), angle (${\theta}$), and arc-tochord ratio (r), are extracted from these segments. These features are used in a neural classifier so that the numerals are recognized. Other existing features are also considered for being recognized in the neural classifier, in order to perform a comparative analysis. We carried out a simulation on a large data set and conducted a comparative analysis with other features with respect to recognition accuracy and time requirements. Furthermore, we also applied the feature to the numeral recognition of two other languages-Bangla and English. In general, we observed that our proposed contour features outperform other schemes.