基于K-means和特征提取的植物叶部病害检测与实现

针对植物常见叶部病害的检测并提高准确率，提出了基于K-means的图像分割和颜色特征提取的算法。以苹果枯叶病为研究对象，应用K-means算法先进行病斑叶片的图像分割，再提取三阶颜色矩参数，与正常叶片参数进行对比分析；实验测试表明，该方法能较好的识别苹果枯叶病，具有较好的鲁棒性，且准确率较高。

Detection of Plant Leaf Diseases Based on K-means and Feature Extraction

Focus on detection of common leaf diseases of plants and improvement of detection accuracy, an algorithm for image segmentation and color feature extraction was proposed in this paper based on K means. With apple blight as the research object, the K means algorithm was used to segment the diseased leaves first, and then the third order color moment parameters were extracted compared with normal leaf parameters.This experiment showed that the method can better identify apple leaf blight and has good robustness and high accuracy.