Multi-layer neural networks for image analysis of agricultural products

被引：86

作者：

Jayas, DS ^{[1
]}

Paliwal, J ^{[1
]}

Visen, NS ^{[1
]}

机构：

[1] Univ Manitoba, Dept Biosyst Engn, Winnipeg, MB R3T 5V6, Canada

来源：

JOURNAL OF AGRICULTURAL ENGINEERING RESEARCH | 2000年 / 77卷 / 02期

关键词：

D O I：

10.1006/jaer.2000.0559

中图分类号：

S2 [农业工程];

学科分类号：

0828 ;

摘要：

Neural networks have recently gained popularity as an alternative to regression models to characterize biological processes. Their decision-making capabilities can be best used in image analysis of biological products where the shape and size classification is not governed by any mathematical function. This paper reviews the technique of image analysis of agricultural products with reference to use of neural network classifiers for decision making. A thorough review of published literature reveals that, although many neural network classifiers have been used and evaluated for classifying agricultural products, multi-layer neural network classifiers perform the best for such tasks. (C) 2000 Silsoe Research Institute.

引用

页码：119 / 128

页数：10