Aim: The primary goal of this study paper is to identify plant leaf disease to discover the greatest accuracy using K-Nearest Neighbors (KNN) and an Innovative Convolutional Neural Network (CNN). Methods and Materials: The data set in this present work utilizes the publicly available Kaggle data set for plant leaf disease detection. The sample size of classification of leaf disease detection with improved accuracy rate was sample 80 (Group 1=40 and Group 2 =40) and calculation is carried out utilizing G-power of 0.8 with alpha and beta qualities are 0.05, 0.2 with a confidence interval at 95%. Accuracy is performed with the dataset from the Kaggle. The two groups are K-Nearest Neighbors (N=10) and Convolutional Neural Network algorithms (N=10 ). Results: An Innovative Convolution Neural Network (CNN) is preferred for the Identification of Plant Leaf Disease. The accuracy is analyzed based on two algorithms, in which CNN reported accuracy of 93.68% and KNN reported accuracy of 81.31% for plant leaf disease detection. The two algorithms CNN and KNN are statistically satisfied with the independent sample T-Test (????=.001) value (p<0.05) i.e. p=0.0321 Conclusion: Identification of Plant Leaf Disease significantly seems to be better in CNN than KNN.