• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1301-1304
• /
• 1998

Several neural networks have been successfully used to classify complex patterns such as handwritten numerals or words. This paper describes the discrimination of totally unconstrained handwritten numerals using the proposed chaotic neural network (CNN) to improve the recognition rate. The recognition system in the paper consists of the preprocessing stage to extract features using Kirsch mask and the classification stage to recognize numerals using the CNN. In order to evaluate the performance of the proposed network, we performed the recognition with unconstrained handwritten numeral database of Concordia university, Canada. Experimental results show that the CNN based recognizer performs higher recognition rate than other neural network-based methods reported using same database.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.913-916
• /
• 1998

In this paper, to provide the robustness of character recognition, we propose a recognition method using the dilated boundary curve feature which has the invariance characteristics for the shift, scale, and rotation changes of character pattern. And its some characteristics and effectieness are evaluated through the experiments for both the english alphabets and the numeral digits. The feature vector is represented by the fourier descriptor for a boundary curve of the dilated character pattern which is generated by the circular mask dilation method, and is used for a nearest neighbort classifier(NNC) or a nearest neighbor mean classifier(NNMC). These the processing time and the recognition rate, and take also the robustness of recognition for both some internal noise and partial corruption of an image pattern.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.1
• /
• pp.48-53
• /
• 2002

In this paper, we presented a new approach to the recognition of unconstrained handwritten numerals using an improved RBF(Radial Basis Function) Neural Networks. The RBF Neural Networks used Raised Cosine as a basis function to improve discrimination and reduce processing time. The performance of Raised Cosine RBF Neural Networks classifier was evaluated using totally unconstrained handwritten numeral database of Concordia University, Montreal, Canada, and the experimental results showed the recognition rate of 98.05%.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.4 s.304
• /
• pp.43-50
• /
• 2005

This paper proposes a new pattern recognition system combining the new adaptive feature weighting based on the genetic algorithm and the modified KNN(K Nearest-Neighbor) rules. The new feature weighting proposed herein avoids the overfitting and finds the Proper feature weighting value by determining the middle value of weights using GA. New GA operators are introduced to obtain the high performance of the system. Moreover, a class dependent feature weighting strategy is employed. Whilst the classical methods use the same feature space for all classes, the Proposed method uses a different feature space for each class. The KNN rule is modified to estimate the class of test pattern using adaptive feature space. Experiments were performed with the unconstrained handwritten numeral database of Concordia University in Canada to show the performance of the proposed method.

• Korean Journal of Cognitive Science
• /
• v.7 no.1
• /
• pp.75-84
• /
• 1996

In this paper we emphasize the importance of architectural aspects of designing a handwritten numeral recognition program. and describe two architectural design.First, we describe the modular design of a numeral recognition program, and mention its advantages.In this design, a recognizer is composed of 10 binary subrecognizers each of which is responsible for only one class.Rule-based training and neural-based training are presented.Second, we connect two(or more)recognizers serially which we call pipelining connection.The second recognizer may act as verifier for the patterns recognized by the forst recognizer, or as second chance recognizer for the patterns rejected by the first recognizer.Our experimental results obtained till now show the merits of the proposed architectural designs.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.707-712
• /
• 1998

This paper presents several softcomputing techniques such as neural networks, fuzzy logic and genetic algorithms : Neural networks as brain metaphor provide fundamental structure, fuzzy logic gives a possibility to utilize top-down knowledge from designer, and genetic algorithms as evolution metaphor determine several system parameters with the process of bottom up development. With these techniques, we develop a pattern recognizer which consists of multiple neural networks aggregated by fuzzy integral in which genetic algorithms determine the fuzzy density values. The experimental results with the problem of recognizing totally unconstrained handwritten numeral show that the performance of the proposed method is superior to that of conventional methods.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.117-120
• /
• 2000

최근 전자상거래 시스템을 이용이 많아짐에 따라, 상품의 정보나 거래를 위한 정보가 되는 수사추출에 관한 연구가 필요하다. 수사는 표현 자체의 다양성과 다근 품사와는 구분되는 활용으로 인해 언어 분석에 있어 많은 문제점을 가지고 있지만, 일반문서에서는 발생빈도가 그다지 높지 않아 그에 관한 연구들은 적은 실정이다. 현재가지의 수사 추출에 관한 연구는 수사 어절이 다른 표현들과는 달리 어순이 뚜렷하다는 것을 이용하여 그 어순들의 결합정보의 조합을 이용하여 시도하였다. 본 논문에서는 이러한 수사 어절의 특징을 문법화함으로써 자연언어 질의에 의한 전자상거래 시스템에 관한 연구를 수행하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.661-663
• /
• 2002

필기체 숫자 인식을 위한 새로운 특징 추출방범을 숫자의 기하학적인 구조들을 이용하여 연구 제안하였다. 일반적으로 쓰이고 있는 특징점들의 몇가지 부류를 결정하여 추줄하였고, 분절 화소들을 이용한 특징 추출기는 사소한 부분들을 명확한 특징으로 탐지하여 추줄하게 된다. 신경망은 새로운 접근 가능성을 탐지하는 실험 인식기로 사용하였고, 이러한 방법들을 이용하여, 일반적인 특징점 추줄방법과 본 연구에서 제안하는 특징점 추출방법을 결합하게 되면 필기체 문자의 인식률이 단순히 일반적인 특징만을 활용하여 얻는 인식률 보다 훨씬 향상됨을 보여주었다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.245-248
• /
• 2002

OCR 시스템에서 feature는 인식성능에 상당히 중요한 역할을 한다. gradient feature는 현재까지 개발되어진 여러 가지 feature들 중에서 폭넓게 사용되고 있는 것 중의 하나이다. 본 논문에서는 변형이 심한 인쇄체 숫자를 실험대상으로 하고, Kirsch mask를 이용한 방향성을 가지는 edge를 추출하여 신경망의 입력벡터로 사용할 때 압축의 크기에 따른 인식성능의 차이를 비교하고, 최적의 벡터크기를 제안한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.762-765
• /
• 2003

본 논문에서 제안하는 분절된 화소들의 특징추출 방법은 이진화 영상에서 수직/수평 화소들의 분절점을 탐색하여 추출하는 특징 탐색기이다. 숫자의 구조적인 면을 고려하여 사소한 부분들도 명확한 특징으로 탐지하여 추출하였고, 이러한 방법은 일반적으로 사용하여지는 특징추출방법 몇가지를 선택하여 이용하였고, 제안하는 방법과 결합하여 필기체 숫자를 인식하였다. 인식기를 구현하기 위하여 3개층 구조를 갖는 클러스터 MLP 신경망을 사용하였다 실험 결과 단순히 일반적인 특징만을 활용하여 얻는 인식률 보다 훨씬 향상됨을 보여주었다.