基于Android的植物叶片图像病害检测  

Plant leaf image disease detection based on Android

作　　者：夏永泉[1] 王会敏[1] 曾莎[1] 

机构地区：[1]郑州轻工业学院计算机与通信工程学院,河南郑州450001

出　　处：《郑州轻工业学院学报（自然科学版）》2014年第2期71-74,共4页Journal of Zhengzhou University of Light Industry:Natural Science

基　　金：国家自然科学基金项目(61302118);河南省高校青年骨干教师资助计划项目(2010GGJS-114)

摘　　要：针对目前农业智能系统开发平台多基于Windows Mobile操作系统,开源性、免费性和人机交互性等方面较差等问题,提出了基于Android平台的一种最大类间差法和Canny算子结合的植物叶片图像病害检测方法.该方法首先用自适应中值滤波对叶片图像进行平滑处理,再对图像进行灰度变换,然后用最大类间差法对图像进行二值化,最后基于Canny算子对图像进行边缘检测.实验结果表明,该方法实现了Android平台下的图像检测,能有效减少边缘噪声,并且能够有效提取叶片图像病害部分的边缘,具有很好的鲁棒性、有效性和准确性.Aiming at the poor performance of agricultural intelligence development platform in open source,free charge and human-computer interaction based on Windows Mobile,under Android platform,a method of leaf image disease detection based on maximum between-cluster variance and Canny operator was proposed. Firstly,adaptive median filter was used to smooth leaf images. Secondly,the images were processed by grey scale transformation. Then,the transformed images were segmented to bi-value images by adopting a method based on maximum between-cluster variance. Finally,the bi-value images images were processed by edge detection based on Canny operator. Experimental result showed that this method achieved leaf image disease detection under Android platform. The method which could reduce marginal noise and extract the edge of leaf image disease effectively provided robustness,effectiveness and correctness.

关 键 词：Android终端 植物叶片图像 病害检测 最大类间差法 CANNY算子 自适应中值滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]