基于计算机视觉的植物黑腐病病斑分析

The Analysis of Black Rot Spot Based on Computer Vision

给出一种基于图像处理和神经网络技术进行植物黑腐病病斑分析的方法,即利用图像处理技术提取病斑的几何特征和颜色特征,其中几何特征根据病斑形状提取,并基于HSV空间提取病斑颜色矩结合红绿颜色特征作为病斑的颜色特征,最后利用神经网络加以识别,从而判断病斑所处的生长周期。给出系统的总体设计和实现方案,研究结果表明,该系统获得了较为理想的检测效果。这一思路为植物病害检测和分析提供一种新的方法。

This paper provides a new method of analyzing black rot spot based on technologies of digital image processing and Neural Network, The technology of image processing is made use of extracting geometrical features and color features of some images. The geometrical features are extracted based on spot shape, and the color features are extracted by spot color moments and red -green color characters. After that, the network is made use of identifying. In this paper, not only an overall system design but also the solution scenario has been provided, The results show that this system performance can make an ideal effect. A new method of automatically identifying can be obtained by exerting this idea provided by this paper.