Fruit Disease Detection by using Naive Bayes Classifier

Diseases in fruit cause a catastrophic problem and leads to economic and agricultural industry loss. Earlier infected fruit had detected manually but now with the advancement in technology image processing techniques have been developed. This framework works in two phases: training and testing. In training phase, all the data related to the non-infected and infected fruit is stored and in testing phase, it is analyzed that whether the fruit is infected or not and if yes then by which disease. In this paper, the technique was developed by combining K-mean clustering algorithm, speedup robust feature (SURF) feature detector and Naive Bayes Classifier and implemented to detect the infected and non-infected fruit. The experiments are performed on fruit database and results are compared with neural network. The results show the superiority of the method with Naive Bayes Classifier.