Knowledge extraction from scenery images and recognition using fuzzy inference neural networks

被引：2

作者：

Iyatomi, H ^{[1
]}

Hagiwara, M ^{[1
]}

机构：

[1] Keio Univ, Fac Sci & Technol, Yokohama, Kanagawa 2238522, Japan

来源：

ELECTRONICS AND COMMUNICATIONS IN JAPAN PART II-ELECTRONICS | 2003年 / 86卷 / 03期

关键词：

neural network; fuzzy inference; scenery image; knowledge extraction; image recognition;

D O I：

10.1002/ecjb.10138

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A new method of extracting various types of human knowledge from scenery images in linguistic form and labeling the various regions of unknown images in an effective manner is proposed. In this system, partitioning of the input/output space can be performed in a self-organizing manner. Rule extraction is performed in parallel and automatically by using a knowledge extraction network (KEN). Depending on the type of image to be learned, two-phase processing including a self-organization phase and an LMS learning phase is performed by several KENs. The overall network output is then unified and knowledge extraction and region recognition are performed linguistically. Software that performs a series of such operations has been implemented and it has been confirmed that knowledge extraction and better image recognition can be performed linguistically even if human knowledge is not provided. (C) 2003 Wiley Periodicals, Inc.

引用

页码：82 / 90

页数：9

共 15 条

[1] BRUCE AD, 1989, INT J COMPUT VISION, V2, P209
[2] Ghosh A., 1993, IEEE Transactions on Fuzzy Systems, V1, P54, DOI 10.1109/TFUZZ.1993.390285
[3] Hirata S., 1992, Transactions of the Institute of Electronics, Information and Communication Engineers D-II, VJ75D-II, P1839
[4] IKEDA, 1996, T IEICE D, V79, P1025
[5] IWADA M, 1997, T IEICE D, V80, P2995
[6] Iyatomi H, 1998, IEEE SYS MAN CYBERN, P4486, DOI 10.1109/ICSMC.1998.727557
[7] THE SELF-ORGANIZING MAP
KOHONEN, T
[J]. PROCEEDINGS OF THE IEEE, 1990, 78 (09) : 1464 - 1480
[8] Fuzzy inference neural network
Nishina, T
Hagiwara, M
[J]. NEUROCOMPUTING, 1997, 14 (03) : 223 - 239
[9] NOGAMI Y, 1997, IEEE INT C SMC, V1, P524
[10] SAKATA, 1997, T IEICE D, V80, P2995

← 1 2 →