Identification of Sunflower Leaf Diseases Based on Random Forest Algorithm

Using digital image processing and machine learning technology to realize the automatic recognition of plant leaf diseases is of great significance to the prevention and control of crop diseases. In this paper, powdery mildew, bacterial leaf spot, black spot and downy mildew of sunflower leaves were studied. The image samples were denoised by morphological weight adaptive image denoising method. K-means + + clustering algorithm and watershed algorithm are used to segment the image of sunflower leaf disease. 19 feature values of color feature and texture feature are extracted from the diseased areas, and a random forest algorithm is constructed to identify the diseased areas. The overall recognition rate can reach 95%.