Based on prior findings, farmers can spot plant infections by keeping an eye out for spots on leaves and leaf yellowing. However, experts believe that technology can support farmers in the early diagnosis of plant diseases. Researchers created a system that makes it simple for farmers to upload images of leaves and receive information about them, such as whether they are healthy or not, and, in the event that they are not, alternative treatments. The researchers employed Convolutional Neural Networks (CNNs), a subset of Artificial Neural Networks (ANNs), for their study. Their CNN model was trained on a dataset consisting of 4,500 leaf images categorized into four different classes. It’s worth noting that the Plant Village collection used for training comprised single-leaved plants with a uniform background and minimal noise, which contrasts with the potential variability in real-world images. To enhance the model’s performance in both simulated and real-world scenarios, they incorporated the You Only Look Once (YOLO) technique to compute Regions of Interest (ROI) within the images. These ROIs were then fed into the CNN model for prediction. The CNN model itself comprises a total of 10 layers, including 2 sequential layers for input preprocessing and augmentation, 3 convolution layers, 3 pooling layers, 1 fully connected layer, and 1 output layer equipped with a SoftMax activation function. The dataset was divided into three sets for training (60%), validation (20%), and testing (20%) to evaluate the model’s performance effectively. The framework was trained in this study over the course of 60 iterations. The proposed, created, and trained model has a 96% accuracy for validation and a 93% accuracy for the test.