The three stages of a strawberry plant's life are seedling, blooming, and crop. It requires distinct conditions for acclimatization during these phases of life. Regretfully, a few maladies drastically reduce the number of strawberries produced. Strawberry disease detection requires the computerization of agriculture and image perception technologies. Convolutional neural network (CNN) model image recognition method for strawberry disease detection has been developed. CNN is a potent deep-learning technique that has been applied to improve image identification. One thousand photos of the strawberry plant from village bapora have been compiled into a dataset. Matrix Laboratory (MATLAB) was used to perform classification using convolutional neural networks using this dataset. The captured image was processed in VGGNet architecture. The following strawberry diseases are detected using the suggested method using two distinct datasets that contain the primary and characteristic images. The features image dataset yielded an accuracy rate of 96.26 % in 15 epochs, which was higher than the 10 % obtained from the primary dataset. This proposed model provides an accessible, accurate, and economical technique for detecting strawberry diseases.