Study on classification of maize disease image based on fast k-nearest neighbor support

Maize disease is the main factor affecting maize yield. Using artificial intelligence method to identify maize diseases is an effective method to prevent maize disease. At present, the method for identifying corn disease images is mainly to classify disease images by means of support vector machines. However, the traditional support vector machine algorithm can not meet the consistency requirements of the algorithm, and can not effectively solve the classification problem of non-convex data sets. Based on the problems existing in SVM mentioned above, we propose a new algorithm of corn disease Image intelligent recognition, which can effectively solve the classification problem of non-convex data sets and satisfy the consistency principle of the algorithm. Experiments on real-world data show that our method has certain advantages in classification accuracy and classification time, and can effectively identify and prevent Maize diseases.