• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.339-346
• /
• 2003

This paper proposes a multiple classifier system having massive micro classifiers. The micro classifiers are trained by using a local set of training patterns. The k nearest neighboring training patterns of one training pattern comprise the local region for training a micro classifier. Each training pattern is incorporated with one or more micro classifiers. Two types of micro classifiers are adapted in this paper. SVM with linear kernel and SVM with RBF kernel. Classification is done by selecting the best micro classifier among the micro classifiers in vicinity of incoming test pattern. To measure the goodness of each micro classifier, the weighted sum of correctly classified training patterns in vicinity of the test pattern is used. Experiments have been done on Elena database. Results show that the proposed method gives better classification accuracy than any conventional classifiers like SVM, k-NN and the conventional classifier combination/selection scheme.

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.93-97
• /
• 1996

본 논문에서는 2 계층 분류기를 이용하여 일반적인 문서(보고서, 책, 잡지, 워드프로세서에서 출력 된 양식) 내의 다중 크기 및 다중 활자체의 인식을 위한 효과적인 방법을 제안하고 구현하였다. 다중언어 문자를 효과적으로 인식하기 위한 2 계층 분류기를 제안하였는데 이는 폰트 독립적 분류기와 폰트 의존적 분류기로 구성되어 있다. 제안된 방법의 성능 평가를 위하여 사무실에서 많이 사용하는 59 종류의 폰트와 각 폰트 당 3가지 크기의 글꼴과, 스캐너에서 지원되는 3가지 농도의 총 489개의 서로 다른 부류를 갖는 3,593,172 자를 대상으로 학습시킨 뒤에 일반 문서를 가지고 펜티엄 PC 상에서 인식 실험을 수행하였다. 실험 결과, 2계층 분류기를 갖는 시스템에서 96-98%의 인식률과 초당40자 이상의 인식 속도를 보여줌으로써 일반적인 문서에서 다중 크기 및 다중 활자체의 문자 인식에 매우 실용적인 가치가 있음을 확인했다.

• Journal of the Korean Society for Railway
• /
• v.12 no.2
• /
• pp.285-290
• /
• 2009

This paper implemented a Speech Recognition System in order to recognize Commands of Ticketing Machine (314 station-names) at real-time using Continuous Hidden Markov Model. Used 39 MFCC at feature vectors and For the improvement of recognition rate composed 895 tied-state triphone models. System performance valuation result of the multi-speaker-dependent recognition rate and the multi-speaker-independent recognition rate is 99.24% and 98.02% respectively. In the noisy environment the recognition rate is 93.91%.

• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.233-238
• /
• 2010

In this paper, we propose a multiple classifier combination method based on image degradation modeling to improve recognition performance on low-quality images. Using an image degradation model, it generates a set of classifiers each of which is specialized for a specific image quality. In recognition, it combines the results of the recognizers by weighted averaging to decide the final result. At this time, the weight of each recognizer is dynamically decided from the estimated quality of the input image. It assigns large weight to the recognizer specialized to the estimated quality of the input image, but small weight to other recognizers. As the result, it can effectively adapt to image quality variation. Moreover, being a multiple-classifier system, it shows more reliable performance then the single-classifier system on low-quality images. In the experiment, the proposed multiple-classifier combination method achieved higher recognition rate than multiple-classifier combination systems not considering the image quality or single classifier systems considering the image quality.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.20-27
• /
• 2004

We propose the character recognition system for Gerber files. The Gerber file is the vector-formatted drawing file for PCB manufacturing, which includes various symbols, figures and characters. Also, the characters are written in horizontal, vertical, and reverse-vortical directions. In this paper, we newly propose the Gerber-character recognition system to recognize all of component names located in PCB. To improve the performance, we develop the multiple recognizers by neural networks and the verifier considering the structural features. The developed system has been installed to the auto-programming software for PCB assembly and inspection machines.

• Journal of KIISE:Software and Applications
• /
• v.34 no.4
• /
• pp.377-388
• /
• 2007

In this paper, we propose a multi-modal biometric system based on face, iris and fingerprint recognition system. To effectively aggregate two systems, we use statistical distribution models based on matching values for genuine and impostor, respectively. And then, We performed reveal fusion algorithms including weighted summation, Support Vector Machine(SVM), Fisher discriminant analysis, Bayesian classifier. From the various experiments, we found that the performance of multi-modal biometric system was influenced with the normalization methods and classifiers.

• Information and Communications Magazine
• /
• v.11 no.5
• /
• pp.23-32
• /
• 1994

편입력 기능을 창작한 시스템의 문자입력 기능에서 사용자들의 다양한 형태의 필기문자를 인식하여 사용자의 만족을 극대화 시킬 수 잇는 고성능의 인식기를 만들기 위해서는 상황과 장소에 따라서 변하는 필기형태를 학습할 수 있는 다이나믹한 인식기 개발이 절대적으로 필요하다고 판단된다. 또한 국제 경쟁력을 갖기 위해서는 사용자의 국적(nationality)에 따라 다양한 자종을 인식할 수 잇는 기능이 있어야 한다. 따라서 본 논문에서는 다양한 사용자의 요구를 만족시키기 위하여 인식기 설계시 필요한 design issues와 philosophy를 제시하고, 이를 기초로 학습기능, 국제화, 소형화의 특징을 갖는 학습기능 다중언어(multilingual) 인식기 설계 방법을 제안하고자 한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.49-54
• /
• 2006

The recent fingerprint recognition system has unstable factors, such as copy of fingerprint patterns and hacking of fingerprint feature point, which mali cause significant system error. Thus, in this research, we used the fingerprint as the main recognition device and then implemented the multi-biometric recognition system in serial using the speech recognition which has been widely used recently. As a multi-biometric recognition system, once the speech is successfully recognized, the fingerprint recognition process is run. In addition, speaker-dependent DTW(Dynamic Time Warping) algorithm is used among existing speech recognition algorithms (VQ, DTW, HMM, NN) for effective real-time process while KSOM (Kohonen Self-Organizing feature Map) algorithm, which is the artificial intelligence method, is applied for the fingerprint recognition system because of its calculation amount. The experiment of multi-biometric recognition system implemented in this research showed 2 to $7\%$ lower FRR (False Rejection Ratio) than single recognition systems using each fingerprints or voice, but zero FAR (False Acceptance Ratio), which is the most important factor in the recognition system. Moreover, there is almost no difference in the recognition time(average 1.5 seconds) comparing with other existing single biometric recognition systems; therefore, it is proved that the multi-biometric recognition system implemented is more efficient security system than single recognition systems based on various experiments.

• Proceedings of the KSLP Conference
• /
• 2003.11a
• /
• pp.230-232
• /
• 2003

음성에 관련된 연구분야에 있어서 음성 데이터 수집의 중요성은 매우 크다. 개발된 인식기나 분석기의 성능이 좋다 하더라도 실험에 사용된 음성 데이터의 질과 양에 따라서 실험 결과를 확정짓기가 어려운 점이 있다. 대개의 경우 음성 수집은 오프라인으로 이루어지는데, 실험에서 요구되는 특정 수집자에 대해서 일정 기간과 정해진 장소에서 반복 수집하는 것은 어려움이 많이 따른다. 그러므로 본 연구에서는 Web을 이용하여 음성 데이터 수집자로 하여금 다양한 시간과 장소에서 자유롭게 음성을 수집할 수 있도록 하였다. 이에 대하여 수집된 음성 데이터의 크기가 커짐에 따른 통신상에서 종종 발생하는 문제점을 개선하려는 목적으로 다중 서버를 두어 수집된 데이터는 지역 서버에 일단 저장되었다가 적절한 상황에서 메인 서버로 자동 전송하는 시스템을 구축하였다. 본 시스템은 서로 다른 실험에서 수집되는 데이터를 수집 지역서버를 지정해 줌으로서 수집자가 원하는 특정 지역 서버에서 별도로 관리할 수 있도록 구성되어 있다. 시간, 위치의 제약 없이 인터넷이 연결된 장소에서는 음성을 수집할 수 있고, 웹상 ActiveX 프로그램을 제공함으로써 일관된 끝점처리 및 잡음처리 기능을 반영할 수 있다. 또한 다양한 응용에 적절한 수집기의 인터페이스를 관리자 모드에서 변경하여 사용할 수 있도록 함으로서 넓은 층에서의 활용도를 높였다. (중략)

• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1684-1690
• /
• 2004

This paper presents a method for classifier selection that uses distribution information of the training samples in a small region surrounding a sample. The conventional DCS-LA(Dynamic Classifier Selection - Local Accuracy) selects a classifier dynamically by comparing the local accuracy of each classifier at the test time, which inevitably requires long classification time. On the other hand, in the proposed approach, the best classifier in a local region is stored in the FSA(Feature Space Attribute) table during the training time, and the test is done by just referring to the table. Therefore, this approach enables fast classification because classification is not needed during test. Two feature space attributes are used entropy and density of k training samples around each sample. Each sample in the feature space is mapped into a point in the attribute space made by two attributes. The attribute space is divided into regular rectangular cells in which the local accuracy of each classifier is appended. The cells with associated local accuracy comprise the FSA table. During test, when a test sample is applied, the cell to which the test sample belongs is determined first by calculating the two attributes, and then, the most accurate classifier is chosen from the FSA table. To show the effectiveness of the proposed algorithm, it is compared with the conventional DCS -LA using the Elena database. The experiments show that the accuracy of the proposed algorithm is almost same as DCS-LA, but the classification time is about four times faster than that.