采用改进遗传算法提取大豆叶片病斑图像

Extraction of the image of soybean target leaf spot based on improved genetic algorithm

摘要: 为了实现大豆叶斑病病斑区域的提取与特征计算，综合运用计算机数字图像处理技术与遗传算法进行大豆病斑提取研究。首先通过计算机视觉技术采集大豆病叶图像；其次，采用遗传算法完成了对病斑区域的提取；最后，运用数字图像处理技术完成了对病斑区域相关特征值的计算。试验结果表明，所提出的方法能够有效地提取出大豆病斑图像区域，并计算出相关特征值，为将来病种的识别和诊断奠定先期基础。

Abstract: Aiming at extracting the image of diseased spots and calculating the feature parameters of diseased spots, the present paper studied the extracting method of soybean diseased spots, which used computer digital image processing and genetic algorithm. First, the authors obtained the image, and then recognized the diseased spots through genetic algorithm. At last, the feature parameters of diseased spots were calculated by using the technology of digital image processing. The results indicate that this method can extract the image of diseased spots efficaciously and calculate the feature parameter accurately, which can provide the foundation for recognition of disease category in advance.