• Journal of information and communication convergence engineering
• /
• v.6 no.1
• /
• pp.100-104
• /
• 2008

Generally, it is difficult to find constant patterns on identifiers in a container image, since the identifiers are not normalized in color, size, and position, etc. and their shapes are damaged by external environmental factors. This paper distinguishes identifier areas from background noises and removes noises by using an ART2-based quantization method and general morphological information on the identifiers such as color, size, ratio of height to width, and a distance from other identifiers. Individual identifier is extracted by applying the 8-directional contour tracking method to each identifier area. This paper proposes a refined ART2-based RBF network and applies it to the recognition of identifiers. Through experiments with 300 container images, the proposed algorithm showed more improved accuracy of recognizing container identifiers than the others proposed previously, in spite of using shorter training time.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.675-676
• /
• 2008

This paper presents adjustment of input order to improve clustering performance of ART1. We propose new method for On-line clustering which adjusts initial input data using buffer. We demonstrate the clustering performance of the proposed algorithm by testing it on Zoo data set from UCI and created artificial data set for simulation. Experimental results show that preposed method increases 7.8% of clustering performance than ART1 model on the average.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.01a
• /
• pp.343-345
• /
• 2016

본 논문에서는 아동이 그린 그림에 대해 ART2 알고리즘을 적용하여 색채 정보를 군집화하고, 군집화 된 색채 정보의 중심 벡터 값들을 퍼지화 한다. 퍼지화 된 색채 정보의 소속도를 퍼지 추론 규칙에 적용한 후에 비퍼지화 한다. 비퍼지화 된 결과를 적용하여 아동의 심리 상태를 분석한다. 제안된 방법을 실험하여 알슐러와 해트윅(Alschuler and Hattwick)의 색채에 따른 심리 상태와 비교한 결과, 제안된 심리 분석 방법이 알슐러와 해트윅의 색채에 따른 심리 상태 분석 결과와 거의 일치하는 것을 확인하였다.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2004.05a
• /
• pp.30-35
• /
• 2004

Several roll motion reduction devices are reviewed and suggested for the application in FPSO. The firstly suggested solution is the shape of the bilge. The next is a bilge keel. The last suggestion is the ART (anti-rolling tank). Typical U-tube type ART is designed for a FPSO and examined extensively by model experiment. The model section was made of transparent acryl. Free decay test, forced oscillation test and wave test were carried out at a two-dimensional wave flume. U-tube type ART is effective only when the natural periods of ART and ship are same. Therefore, the divided U-tube type ART with split plate is suggested for the reduction of the roll motion of a FPSO over the wide range of the roll period.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.305-308
• /
• 2003

This paper proposed Ellipsoid Fuzzy-ART (Fuzzy-Adaptive Resonance Theory) for recognition performance improvement to use Mahalanobis distance. The suggested method uses Mahalanobis distance to decide pattern boundary region at vector space. In order to confirm the validity of proposed method, comparison of the performance has made between existing method and the proposed method through simulation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.4
• /
• pp.883-889
• /
• 2005

Error backpropagation algorithm of multilayer perceptron may result in local-minima because of the insufficient nodes in the hidden layer, inadequate momentum set-up, and initial weights. In this paper, we proposed the ART-1 based fuzzy supervised learning algorithm which is composed of ART-1 and fuzzy single layer supervised learning algorithm. The Proposed fuzzy supervised learning algorithm using self-generation method applied not only ART-1 to creation of nodes from the input layer to the hidden layer, but also the winer-take-all method, modifying stored patterns according to specific patterns. to adjustment of weights. We have applied the proposed learning method to the problem of recognizing a resident registration number in resident cards. Our experimental result showed that the possibility of local-minima was decreased and the teaming speed and the paralysis were improved more than the conventional error backpropagation algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.5
• /
• pp.1004-1012
• /
• 2007

In this paper, we proposed a new car license plate recognition method using an unsupervised ART2 algorithm with HSI color model. The proposed method consists of two main modules; extracting plate area from a vehicle image and recognizing the characters in the plate after that. To extract plate area, hue(H) component of HSI color model is used, and the sub-area containing characters is acquired using modified fuzzy binarization method. Each character is further divided by a 4-directional edge tracking algorithm. To recognize the separated characters, noise-robust ART2 algorithm is employed. When the proposed algorithm is applied to recognize license plate characters, the extraction rate is better than that of existing RGB model and the overall recognition rate is about 97.4%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.94-96
• /
• 2013

본 논문에서는 복부 초음파 영상에서 Ends_in Search Stretching 기법을 적용하여 명암 대비를 강조한 후, 이진화, 영역 레이블링 기법, 잡음 제거를 통해 근막을 추출하고, 근막 영역의 하단 경계선을 기준으로 Cubic Spline 보간법을 적용하여 복부 근육의 근막 하단 영역을 추출한다. 복부 초음파 영상에서 추출된 근막 하단 영역을 이용하여 근막 영역을 제거한 후, 거리 기반 퍼지 ART 알고리즘을 적용하여 충수 후보 영역을 추출한 다. 추출된 충수 후보 영역에 침식 연산과 영역 레이블링 기법을 적용하여 충수를 추출한다. 제안된 방법을 복부 초음파 영상을 대상으로 실험한 결과, 기존의 충수 추출 방법보다 객관적이고 효율적으로 충수와 소장의 명암도 차이를 구별할 수 있어 충수 영역이 이전의 방법 보다 비교적 정확히 추출되는 것을 영상의학과 관련 전문의를 통해 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.370-376
• /
• 2005

본 논문에서는 HSI 정보와 신경망의 비지도 학습 방법인 ART2 알고리즘을 이용하여 신 차량 번호판을 인식하는 방법을 제안한다. 제안된 방법은 차량의 영상에서 번호판 영역을 추출하는 부분과 추출된 번호판 영역의 문자를 인식하는 부분으로 구성된다. 본 논문에서는 차량 번호판 영역을 추출하기 위해 HSI 컬러 모형의 Hue 정보를 이용하여 차량 번호판 영역을 추출하고 개선된 퍼지 이진화 방법을 적용하여 추출된 차량 번호판 영역으로부터 문자를 포함한 특징 영역을 이치화 한 후에 4방향 윤곽선 추적 알고리즘을 적용하여 개별 코드를 추출한다. 추출된 개별 코드를 인식하기 위해 잡음과 훼손에 비교적 강한 ART2 알고리즘을 적용한다. 제안된 방법의 차량 번호판 추출 및 인식 성능을 평가하기 위하여 실제 비영업용 차량 번호판에 적용한 결과, 기존의 차량 번호판의 추출 방법보다 번호판 영역의 추출률이 개선되었다. 또한 ART2 알고리즘을 적용하여 신 차량 번호판을 인식하는 것이 효율적임을 확인하였다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.4 s.310
• /
• pp.21-29
• /
• 2006

A fuzzy ARTMAP neural network and a fuzzy ART neural network are proposed to identify $H_2S,\;NH_3$, and their mixtures and to estimate their concentrations, respectively. Features are extracted from a tin oxide gas sensor operated in a thermal modulation plan. After dimensions of the features are reduced by a preprocessing scheme, the features are fed into the proposed fuzzy neural networks. By computer simulations, the proposed method is shown to be fast in learning and stable in concentration estimating compared with other methods.