A method to make multiple hypotheses with high cumulative recognition rate using SVMs

被引：13

作者：

Maruyama, K

Maruyama, M

Miyao, H

Nakano, Y

机构：

[1] Shinshu Univ, Dept Informat Engn, Nagano, Japan

[2] Kyushu Sangyo Univ, Intelligent Informat, Higashi Ku, Fukuoka, Japan

来源：

PATTERN RECOGNITION | 2004年 / 37卷 / 02期

关键词：

support vector machines; DAGSVM; JEITA-HP; Max-Win algorithm; rank information; hybrid method;

D O I：

10.1016/S0031-3203(03)00236-X

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes a method to make multiple hypotheses with high cumulative recognition rate using SVMs. To make just a single hypothesis by using SVMs, it has been shown that Directed Acyclic Graph Support Vector Machines (DAGSVM) is very good with respect to recognition rate, leaming time and evaluation time. However, DAGSVM is not directly applicable to make multiple hypotheses. In this paper, we propose a hybrid method of DAGSVM and Max-Win algorithm. Based on the result of DAGSVM, a limited set of classes are extracted. Then, Max-Win algorithm is applied to the set. We also provide the experimental results to show that the cumulative recognition rate of our method is as good as the Max-Win algorithm, and that the execution time is almost as fast as DAGSVM. (C) 2003 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：241 / 251

页数：11

共 16 条

[1] Choosing multiple parameters for support vector machines [J].

Chapelle, O ;

Vapnik, V ;

Bousquet, O ;

Mukherjee, S .

MACHINE LEARNING, 2002, 46 (1-3) :131-159

[2]

CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411

[3]

Duda R. O., 2000, PATTERN CLASSIFICATI

[4]

Heisele B, 2002, ADV NEUR IN, V14, P1239

[5] A comparison of methods for multiclass support vector machines [J].

Hsu, CW ;

Lin, CJ .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (02) :415-425

[6]

Joachims T, 1999, ADVANCES IN KERNEL METHODS, P169

[7]

Joachims T., 1998, Lecture Notes in Computer Science, P137, DOI DOI 10.1007/BFB0026683

[8] Handwritten digit recognition using state-of-the-art techniques [J].

Liu, CL ;

Nakashima, K ;

Sako, H ;

Fujisawa, H .

EIGHTH INTERNATIONAL WORKSHOP ON FRONTIERS IN HANDWRITING RECOGNITION: PROCEEDINGS, 2002, :320-325

[9]

Maruyama K, 2000, P 7 IWFHR, P133

[10] HISTORICAL REVIEW OF OCR RESEARCH-AND-DEVELOPMENT [J].

MORI, S ;

SUEN, CY ;

YAMAMOTO, K .

PROCEEDINGS OF THE IEEE, 1992, 80 (07) :1029-1058

← 1 2 →