• 한국지능시스템학회논문지
• /
• 제18권3호
• /
• pp.373-380
• /
• 2008

지금까지 기계 기반의 필기 숫자 인식 방법에 대한 많은 연구가 진행되어 왔다. 그러나 여전히 인간이 만족할 만한 인식 성능을 이루지는 못하였다. 이러한 배경에는 단순히 인식률을 나타내는 수치가 낮은 것도 한 부분을 차지 하지만, 인간이 수긍할 수 없는 오류 성향도 중요한 부분을 차지한다. 그러므로 본 논문에서는 실제 인간의 숫자 인식이 어떻게 이루어지는지를 확인하는 실험을 먼저 수행하고, 이것에 근거하여 기계 인식을 위하여 필요한 요소들이 무엇인지를 고찰하도록 하였다. 실험결과 한쪽 또는 양쪽 방향으로 혼동하는 숫자 쌍, 전혀 혼동하지 않는 숫자 쌍, 오류 발생의 중복성 등의 결과를 비교 분석하여 인간이 인식과정에서 중요하게 고려하는 특징들을 찾아냈고, 그 결과에 근거하여 기계 인식에 있어서 더 높은 인식 성능을 발휘할 수 있고, 더 나아가 인간적인 측면에서 보다 더 신뢰할 수 있는 인식결과를 이끌어 낼 수 있는 접근 방향에 대하여 제시하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(3)
• /
• pp.33-36
• /
• 2000

In this paper, we describe a study on the spotting and recognition of handwritten numerals using neural networks. To recognize a handwritten numeral, two kinds of neural network classifiers ate developed. One makes use of the positive samples only, while the other does both of the positive and negative samples. We propose two numeral spotters which discriminate between numerals and non-numerals. Those are also implemented by using neural networks. From the various experimental results, we found that our methods can be successfully applied to spot and recognize handwritten numerals.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.609-615
• /
• 1998

In this paper, we propose efficient total recognition system of handwritten and printed numerals for enhancing the classification time. The proposed system consist two step neuroclassifier: Printed numerals classifier and Handwritten numerals classifier. The performance of the propose classifier was tested on 5000 handwritten numerals database of NIST and 100 printed numerals database. In case of handwritten classifier, the overall classification times were 11 second. And in case of proposed system, the overall classification times were reduced by...

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.319-323
• /
• 2022

Handwritten text recognition is one of the active research areas nowadays. The progress in this field differs in every language. For example, the progress in Arabic handwritten text recognition is still insignificant and needs more attentions and efforts. One of the most important fields in this is Arabic handwritten manuscript text recognition which focuses in extracting text from historical manuscripts. For eons, ancients used manuscripts to write everything. Nowadays, there are millions of manuscripts all around the world. There are two main challenges in dealing with these manuscripts. The first one is that they are at the risk of damage since they are written in primitive materials, the second challenge is due to the difference in writing styles, hence most people are unable to read these manuscripts easily. Therefore, we discuss in this study different papers that are related to this important research field.

• 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.

• 전자공학회논문지B
• /
• 제31B권4호
• /
• pp.1-8
• /
• 1994

In this paper, we propose an efficient two-step pattern matching method which promises shape distortion-tolerant recognition of handwritten of handwritten Hangul syllables. In the first step, nonlinear shape normalization is carried out to compensate for global shape distortions in handwritten characters, then a preliminary classification based on simple pattern matching is performed. In the next step, nonlinear pattern matching which achieves best matching between input and reference pattern is carried out to compensate for local shape distortions, then detailed classification which determines the final result of classification is performed. As the performance of recognition systems based on pattern matching methods is greatly effected by the quality of reference patterns. we construct reference patterns by combining the proposed nonlinear pattern matching method with a well-known averaging techniques. Experimental results reveal that recognition performance is greatly improved by the proposed two-step pattern matching method and the reference pattern construction scheme.

• 한국정보통신학회논문지
• /
• 제6권6호
• /
• pp.986-991
• /
• 2002

본 논문에서는 고유벡터를 이용한 오프라인 필기체 숫자인식 기법을 제시한다. 본 기법에서는 KL 변환에 의한 고유벡터를 이용하여 통계적으로 숫자의 특징을 추출하며, 특징공간상에서 최소거리기법으로 숫자를 인식한다. 본 기법에서 제안된 특징추출 방법에서는 많은 표본 숫자영상에서 각 숫자들의 특징을 가장 잘 표현하는 기저벡터를 찾아내고 이로부터 숫자의 특징을 구한다. 제시된 기법의 성능 평가를 위해 Concordia대학의 무제약 필기체 숫자 데이터베이스를 사용하여 실험한 결과 96.2%의 인식률을 얻을 수 있었다.

• 융합신호처리학회논문지
• /
• 제3권1호
• /
• pp.48-53
• /
• 2002

본 논문에서는 무제약 필기체 숫자 인식에 있어서 향상된 RBF(Radial Basis Function) 신경망을 이용한 새로운 접근 방법을 제시하였다. RBF 신경망은 인식률과 인식 속도를 향상시키기 위해 기저 함수로서 Raised Cosine RBF를 사용하였다. Raised Cosine RBF 신경망 분류기의 성능 평가를 위하여 캐나다 몬트리올 Concordia 대학의 무제약 필기체 숫자 데이터베이스를 사용하였고, 실험 결과 98.05%의 인식률을 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.577-580
• /
• 1997

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.581-584
• /
• 1997

Discussed is stroke identification technique for automatic recognition of kanji characters without using the order of drawing strokes of a character.