• Journal of Information Processing Systems
• /
• 제8권4호
• /
• pp.653-668
• /
• 2012

In this study, an improved HMM based recognition model is proposed for online English and Korean handwritten characters. The pattern elements of the handwriting model are sub character strokes and ligatures. To deal with the problem of handwriting style variations, a modified Hierarchical Clustering approach is introduced to partition different writing styles into several classes. For each of the English letters and each primitive grapheme in Korean characters, one HMM that models the temporal and spatial variability of the handwriting is constructed based on each class. Then the HMMs of Korean graphemes are concatenated to form the Korean character models. The recognition of handwritten characters is implemented by a modified level building algorithm, which incorporates the Korean character combination rules within the efficient network search procedure. Due to the limitation of the HMM based method, a post-processing procedure that takes the global and structural features into account is proposed. Experiments showed that the proposed recognition system achieved a high writer independent recognition rate on unconstrained samples of both English and Korean characters. The comparison with other schemes of HMM-based recognition was also performed to evaluate the system.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권12호
• /
• pp.1581-1590
• /
• 2004

본 논문은 한 가지 특징 요소로서 획 방향 코드들만을 사용하는 강건한 오프라인 필기체 숫자 인식 방법을 제안한다. 이 방법은 입력된 숫자 이미지에 대하여 일반적인 8방향 코드를 생성하고 이 코드들의 조합을 다층 신경망에 학습하고 각 숫자를 인식하게 한다. 8방향 코드들은 다양하게 표현된 숫자들의 자기구성 그래프(SOG*:Improved Self-Organizing Graph) 세선화 결과에 의해 만들어지고 이 코드의 사용은 2개 이상의 특징점들을 처리하는 기존의 복합적인 단계들을 단순화시킨다. 실험결과는 모든 숫자 데이타베이스의 어떤 이미지들에 대해서도 인식률이 일관성 있게 98.85% 이상임을 보여준다.

• 비교문화연구
• /
• 제27권
• /
• pp.255-289
• /
• 2012

In the course of completing a National Research Foundation project, I recently found that a handwritten Korean manuscript of The Tale of Mei Fei is kept in the Adan Collection, which is a significant scholarly discovery given that no relevant research is available. The editions of the Tale of Mei Fei available in Korea include ${\ll}$藝苑?華${\gg}$ edition, ${\ll}$說?${\gg}$ edition, and the handwritten manuscript in Korean collected in the Adan Collection. Being the only handwritten Korean translation of the work, the Tale of Mei Fei in the Adan Collection was appended by the translations of ${\ll}$한셩뎨됴비연합덕젼${\gg}$ and ${\ll}$당고종무후뎐${\gg}$. As for the practice of translation of the work, literal "word to word" translation was done for the most part of the text; some sentences were occasionally translated liberally. Also, as for the poems in the text, pronunciation of each Chinese character was provided along with the translated text.

• 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.

• 한국멀티미디어학회논문지
• /
• 제25권7호
• /
• pp.953-963
• /
• 2022

We suggest the development of a mobile muscular savings account application as a more effective and consistent strategy to avoid sarcopenia, one of the elderly diseases, based on the researcher's experience conducting a handwritten 'muscle saving account' in the S city of the metropolitan area. The analysis of currently existent healthcare-related applications shows that muscle strength improvement and maintenance applications are needed to improve easy use and access without burden for elderly users because there are many functions, and it can be difficult for the elderly to use the application. A survey of participants who used handwritten 'muscle savings accounts' was conducted before the design development to measure user satisfaction. Based on this, the suggested application's design is similar to the handwritten type, functionalities are modified for easy usage by the elderly, and information is intuitively comprehended and presented properly using color contrast and Sans serif font. We plan to conduct a survey of the elderly who did not participate in the project as part of follow-up research, and afterward continue the research on the development of customized applications optimized for the prevention of sarcopenia in the elderly for muscle strength improvement and maintenance based on the results.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.89-94
• /
• 2024

Indian subcontinent is a birthplace of multilingual people where documents such as job application form, passport, number plate identification, and so forth is composed of text contents written in different languages/scripts. These scripts may be in the form of different indic numerals in a single document page. Due to this reason, building a generic recognizer that is capable of recognizing handwritten indic digits written by diverse writers is needed. Also, a lot of work has been done for various non-Indic numerals particularly, in case of Roman, but, in case of Indic digits, the research is limited. Moreover, most of the research focuses with only on MNIST datasets or with only single datasets, either because of time restraints or because the model is tailored to a specific task. In this work, a hybrid model is proposed to recognize all available indic handwritten digit images using the existing benchmark datasets. The proposed method bridges the automatically learnt features of Capsule Network with hand crafted Bag of Feature (BoF) extraction method. Along the way, we analyze (1) the successes (2) explore whether this method will perform well on more difficult conditions i.e. noise, color, affine transformations, intra-class variation, natural scenes. Experimental results show that the hybrid method gives better accuracy in comparison with Capsule Network.

• 한국산학기술학회논문지
• /
• 제12권3호
• /
• pp.1417-1426
• /
• 2011

아직도 다양한 비즈니스 현장에서는 업무특성이나 법률적 제약 때문에 종이문서로 정보를 취득하고 있다. 이러한 수기문서는 IT 시스템을 통한 실시간 정보 처리와 관리를 위해 전자화 과정을 거쳐 디지털 문서로 변환되어 야 한다. 기존의 문서 전자화 시스템은 수기문서를 스캐닝과 후처리 작업을 거쳐 전자화하기 때문에 연속적인 업무 처리가 어렵다. 이 논문에서는 디지털펜과 필기체인식 기술을 이용한 수기문서 전자화 프레임워크인 LiveForm을 제안한다. 또한, 제안한 프레임워크의 적용가능성을 보이기 위해 LiveForm 기반 산업특수가스 유통 서비스를 구현하고 적용 효과를 분석한다. LiveForm은 디지털펜으로 절대좌표값이 인쇄된 종이문서를 작성하면 작성문서와 동일한 디지털이미지를 생성하고, 기록 정보는 필기체인식을 통해 디지털 문자로 변환하여 업무시스템에 자동으로 입력한다. LiveForm 기반 응용시스템은 종이문서 기반 정보 취득이 많은 업무에서 문서 전자화를 위한 스캐닝과 데이터 수동입력없이 취득한 정보를 업무시스템 자동으로 반영할 수 있어 업무 프로세스를 대폭 개선할 수 있다.

• 인지과학
• /
• 제6권4호
• /
• pp.51-71
• /
• 1995

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1991년도 춘계공동학술대회 발표논문 및 초록집; 전북대학교, 전주; 26-27 Apr. 1991
• /
• pp.163-163
• /
• 1991

• 정보과학회지
• /
• 제25권1호
• /
• pp.55-58
• /
• 2007