基于改进灰度共生矩阵和粒子群算法的稻飞虱分类

针对稻飞虱远程实时识别采集图像质量不高而无法使用颜色特征的问题,应用灰度共生矩阵提取的纹理特征值对稻飞虱分类进行了研究。采用自行设计的拍摄装置采集稻飞虱图像,经过一系列预处理后得到去掉背景的稻飞虱灰度图像;对灰度图像采用改进的灰度共生矩阵提取纹理特征值,再用反向传播BP（back propagation）神经网络和参数改进粒子群算法优化BP神经网络分别进行训练和测试,以此检验纹理特征值的识别效果和粒子群算法的优化效果。试验用Matlab验证算法,对白背飞虱、灰飞虱和褐飞虱共300个样本进行了训练和测试,结果表明基于参数选择改进粒子群算法优化BP神经网络的识别率总体达到了95%,比直接用BP神经...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 30; no. 10; pp. 138 - 144
Main Author 邹修国 丁为民 陈彩蓉 刘德营
Format Journal Article
LanguageChinese
Published 江苏省现代设施农业技术与装备工程实验室，南京 210031 2014
南京农业大学工学院，南京 210031
Subjects
分类
图像识别
灰度共生矩阵
神经网络
稻飞虱
粒子群
稻飞虱
灰度共生矩阵
neural networks
粒子群
神经网络
particle swarm optimization
rice planthopper
gray level co-occurrence matrix
classification
图像识别
image recognition
分类
Online AccessGet full text
ISSN1002-6819
DOI10.3969/j.issn.1002-6819.2014.10.017

Cover

More Information
Summary:针对稻飞虱远程实时识别采集图像质量不高而无法使用颜色特征的问题,应用灰度共生矩阵提取的纹理特征值对稻飞虱分类进行了研究。采用自行设计的拍摄装置采集稻飞虱图像,经过一系列预处理后得到去掉背景的稻飞虱灰度图像;对灰度图像采用改进的灰度共生矩阵提取纹理特征值,再用反向传播BP（back propagation）神经网络和参数改进粒子群算法优化BP神经网络分别进行训练和测试,以此检验纹理特征值的识别效果和粒子群算法的优化效果。试验用Matlab验证算法,对白背飞虱、灰飞虱和褐飞虱共300个样本进行了训练和测试,结果表明基于参数选择改进粒子群算法优化BP神经网络的识别率总体达到了95%,比直接用BP神经网络的识别率高,而且经过Matlab测试,训练时间只用了0.5683s,说明粒子群算法更满足实时性要求。
Bibliography:11-2047/S
neural networks;image recognition;classification;particle swarm optimization;rice planthopper;gray level co-occurrence matrix
The rice planthopper images acquired by remote real-time recognition system usually have poor quality, and hence it is impossible to classify rice planthoppers using the color features of rice planthopper images. This study proposed to extract texture features of images based on gray level co-occurrence matrix（GLCM） and used the texture features to classify rice planthoppers. A H-shape mobile photographing device designed by us was used to obtain color images of rice planthoppers. The color images were grayed by formula, and then the background of images was removed using Otsu image segmentation method to generate binary images followed by calculation through the binary image coordinates. The GLCM was improved to extract texture features of images without background. Specifically, the center of gravity was determined by coordinates of the images and considered as the center to
ISSN:1002-6819
DOI:10.3969/j.issn.1002-6819.2014.10.017