| 神经网络在储粮害虫识别中的应用 |
| |
| 引用本文： | 邱道尹,张成花,张红涛,沈宪章,岳永娟. 神经网络在储粮害虫识别中的应用[J]. 农业工程学报, 2003, 19(1): 142-144 |
| |
| 作者姓名： | 邱道尹 张成花 张红涛 沈宪章 岳永娟 |
| |
| 作者单位： | 1. 华北水利水电学院
2. 郑州大学 |
| |
| 基金项目： | 中国科学院模式识别国家重点实验室开放基金资助项目(NLPR2000)；河南省自然科学基金资助项目(0211030300) |
| |
| 摘 要： | 重点研究了基于图像识别的储粮害虫自动检测系统中的粮虫分类环节。对分割后的储粮害虫二值化图像，从10多个形态特征中选择出5个有效的特征；将GA和BP算法相结合来训练神经网络，克服了传统BP算法收敛速度慢、易陷入局部极小等缺陷，对4类害虫的20个样本的识别率达到100%，为系统的实际应用奠定了基础。
|
| 关 键 词： | 储粮害虫； 图像识别； 神经网络； BP算法； 遗传算法 |
| 文章编号： | 1002-6819(2003)01-0142-03 |
| 收稿时间： | 2001-08-10 |
| 修稿时间： | 2001-08-10 |
Application of neural networks in the recognition of stored-grain pests |
| |
| Qiu Daoyin,Zhang Chenghu,Zhang Hongtao,Shen Xianzhang and Yue Yongjuan. Application of neural networks in the recognition of stored-grain pests[J]. Transactions of the Chinese Society of Agricultural Engineering, 2003, 19(1): 142-144 |
| |
| Authors: | Qiu Daoyin Zhang Chenghu Zhang Hongtao Shen Xianzhang Yue Yongjuan |
| |
| Abstract: | A study of pest classification in the stored-grain pests automatic detection system based on image recognition was conducted. From the binary pest images, we extracted over ten shape features and finally select five effective features. By combining genetic algorithm with BP algorithm, we trained a multi-layer forward neural network, and overcame the shortcomings of the conventional BP algorithm, such as the slow convergence and its tendency to fall into local minimum. By use of this neural network model, an experiment for recognizing twenty samples of four kinds of stored-grain pests was performed, and the accurate recognition ratio was up to 100 percent. This lays a foundation for the practical use of the system. |
| |
| Keywords: | stored-grain pests image recognition neural network BP algorithm genetic algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《农业工程学报》浏览原始摘要信息 |
|
点击此处可从《农业工程学报》下载全文 |
