Aim: To estimate accuracy in Image plant disease detection using Convolutional Neural Network over KNearest Neighbors. Materials and Methods: Convolutional Neural Network and K-Nearest Neighbors are implemented in this research work. Sample size is calculated using G power software and determined as 10 per group with pretest power 80%. Results and Discussion: Convolutional Neural Network provides a higher of 88.74 compared to K-Nearest Neighbors with 84.52 in predicting plant disease in plant diseases detection. There are statistically significant differences between study groups with p = 0.048 (p<0.05) Independent T-test value states that the results in the study are insignificant. Conclusion: Convolutional Neural Network gives better accuracy then K-Nearest Neighbors.