• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.313-315
• /
• 2003

분할 및 합병 개념에 바탕을 둔 모듈라 신경망이 자동차 번호판 문자 인식에서 단일 신경망 사용 보다 학습 질 측면이나 학습 속도 면에서 좋은 결과를 보였다. 본 논문에서는 번호판 인식을 위한 모듈라 신경망 구성 시, 특징 벡터 클러스터링 방법에 따른 모듈라 신경망의 성능을 평가하였다. K-means Clustering 알고리즘을 이용하여 유사한 특징 벡터를 그룹핑하는 방법과 본 논문에서 제안한 알고리즘을 사용하여 유사하지 않는 특징 벡터들을 그룹핑하는 방법 각각을 구현하여 실험하였다. 실험결과, 유사하지 않는 특징 벡터들로 모듈라 신경망을 구성할 경우가 그렇지 않은 경우보다 좋은 인식 결과를 보였다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.38 no.5
• /
• pp.7-13
• /
• 2001

Modular wavelet neural network combining wavelet theory and modular concept based on single layer neural network have been proposed as an alternative to conventional wavelet neural network and kind of modular network. In this paper, an effective method to construct an optimal modular wavelet network is proposed using genetic algorithm. Genetic Algorithm is used to determine dilations and translations of wavelet basis functions of wavelet neural network in each module. We apply the proposed algorithm to approximation problem and evaluate the effectiveness of the proposed system and algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.568-570
• /
• 2002

최근, 분류기 쪽에서는 모듈라 학습을 이용한 방법들에 대해서 상당한 관심이 모아지고 있다. 모듈라 학습 방법은 divide and conquer 개념에 바탕을 두고 있기 때문에 복잡한 문제에 대해서 학습 질 측면이나 학습 속도 면에서 단일 분류기에 비해 좋은 결과들을 나타내고 있다. 인공신경망을 이용한 분류 방법 쪽에서도 이러한 연구들이 이루어지고 있다. 본 논문에서는 번호판 인식을 위한 간단한 형태의 모듈라 신경망을 제안하고 이의 성능을 평가하였다. 실험 결과, 일반적인 차량 번호판의 영상에서 성공적인 결과를 보였으며, 잡음에 의한 훼손된 번호판도 좋은 인식 결과를 보였다. 또한 인식률 측면 뿐만 아니라 학습 속도 면에서도 상당한 이득이 있었다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.38 no.2
• /
• pp.12-19
• /
• 2001

In this paper, we propose the new algorithm which can design on the optimal structure of modular system. This system is composed to the wavelet neural network in order to simplify the structure of modular system and use the time-frequency analysis. We will determine the number of module and node of each sub-system using the proposed algorithm. This algorithm provides the methodology, which we will design optimal structure of modular wavelet neural network through analyzing the character of system. We apply the proposed new structure and algorithm to approximation problem and evaluate the effectiveness of the proposed system and algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.409-415
• /
• 2003

Recently, the modular learning are very popular and receive much attention for pattern classification. The modular learning method based on the "divide and conquer" strategy can not only solve the complex problems, but also reach a better result than a single classifier′s on the learning quality and speed. In the neural network area, some researches that take the modular learning approach also have been made to improve classification performance. In this paper, we propose a simple modular neural network for characters recognition of vehicle number plate and evaluate its performance on the clustering methods of feature vectors used in constructing subnetworks. We implement two clustering method, one is grouping similar feature vectors by K-means clustering algorithm, the other grouping unsimilar feature vectors by our proposed algorithm. The experiment result shows that our algorithm achieves much better performance.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.796-798
• /
• 2004

기존의 번호판 인식 시스템에서는 대부분 카메라가 고정 상태에서 차량의 전면부를 찍어 영상을 획득하고, 이로부터 번호판을 추출하고 인식한다 그러나 본 연구에서는 기존 연구들과 달리 이동 중인 자동차에 카메라를 설치하여 움직이는 자동차의 영상을 획득하여 번호판을 추출하고 인식한다. 인식하고자 하는 영상이 잡음이나 왜곡 없이 깨끗하다면 인식 과정은 간단하게 수행될 것이다. 그러나, 실제로 얻어진 영상은 간단한 방법으로 인식하기에는 어려올 정도로 왜곡이나 변형이 심한 경우가 많다. 따라서 본 논문에서는 SVM 전단에 모듈라 신경망을 결합하여 인식하는 방법을 사용함으로써 잡음과 같은 변형에 덜 민감하도록 하고자 하였다. 실험결과, 제안하는 분류기를 이용한 방법이 번호판 인식에 우수한 성능을 보임을 확인하였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.2
• /
• pp.32-43
• /
• 2004

In this paper, a system which can effectively recognize the plate image extracted from camera set on a moving car is proposed. To extract car licence plate from moving vehicles, multiple candidates are maintained based on the strong vertical edges which are found in the region of car licence plate. A candidate region is selected among them based on the ratio of background and characters. We also make a comparative study of recognition performance between support vector machines and modular neural networks. The experimental results lead us to the conclusion that the former is superior to the latter. For a better recognition rate, a simple method combining the support vector machine with modular neural network where the output of the latter is used as the input of the former is suggested and evaluated. As we expected, the hybrid one shows the best result among those three methods we have mentioned.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.389-395
• /
• 2006

This paper proposes the controller for biped robot using intelligent control algorithm. In order to simplify the complexity of biped robot control, manipulator of biped robot is divided into four modules. These modules are controlled by intelligent algorithm with Hierarchical Mixture of Experts(HME) using neural network. Also neural network having direct control method learns the inverse dynamics of biped robot. The HME, which is a network of tree structure, reallocates the input domain for the output by learning pattern of input and output. In this paper, as a result of learning HME repeatedly with EM algorithm, the controller for biped robot operating safety walking is designed by modelling dynamics of biped robot and generating virtual error of HME.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.115-118
• /
• 2000

In order to approximate a nonlinear function, modular wavelet networks combining wavelet theory and modular concept based on single layer neural network have been proposed as an alternative to conventional wavelet neural networks and kind of modular network. Modular wavelet networks provide better approximating performance than conventional one. In this paper, we propose an effective method to construct an optimal modualr wavelet network using genetic algorithm. This is verified through experimental results.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.9-14
• /
• 2004

Rational sense is affected by emotion. If we add the factor of estimated emotion by environment information into robots, we may get more intelligent and human-friendly robots. However, various sensory information and pattern classification are prescribed for robots to learn emotion so that the networks are suitable for the necessity of robots. Neural network has superior ability to extract character of system but neural network has defect of temporal cross talk and local minimum convergence. To solve the defects, many kinds of modular neural networks have been proposed because they divide a complex problem into simple several subproblems. The modular neural network, introduced by Jacobs and Jordan, shows an excellent ability of recomposition and recombination of complex work. On the other hand, the recurrent network acquires state representations and representations of state make the recurrent neural network suitable for diverse applications such as nonlinear prediction and modeling. In this paper, we applied recurrent network for the expert network in the modular neural network structure to learn data pattern based on emotional assessment. To show the performance of the proposed network, simulation of learning the environment and behavior pattern is proceeded with the real time implementation. The given problem is very complex and has too many cases to learn. The result will show the performance and good ability of the proposed network and will be compared with the result of other method, general modular neural network.