Modeling of visual flotation froth data

被引：28

作者：

Hyötyniemi, H

Ylinen, R

机构：

[1] Aalto Univ, Control Engn Lab, FIN-02015 Espoo, Finland

[2] Univ Oulu, Syst Engn Lab, FIN-90571 Oulu, Finland

来源：

CONTROL ENGINEERING PRACTICE | 2000年 / 8卷 / 03期

关键词：

sensor fusion; image analysis; feature extraction; flotation froth;

D O I：

10.1016/S0967-0661(99)00187-2

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, the principles of sensor fusion are presented. A new sparse coding method based on a generalization of the generalized Hebbian algorithm (GGHA) is presented. The algorithm is realized using a modification of the Kohonen network. The method is tested on an image analysis of flotation froth, in order to find features corresponding to the poisoning phenomenon in a flotation cell. The features found are capable of predicting the poisoning earlier than the ordinary process instrumentation. (C) 2000 Elsevier Science Ltd. All rights reserved.

引用

页码：313 / 318

页数：6

共 14 条

[1] WHAT IS THE GOAL OF SENSORY CODING [J].