Android Based Plant Diseases Detection Using Convolutional Neural Network

In the near future, the global human population is projected to reach 8.6 billion, driven by exponential growth. This substantial increase in population will necessitate a corresponding surge in both food production and consumption. Crop diseases, which can adversely affect agricultural products during their growth, pose a significant threat to food security. However, the timely identification of such diseases across various regions of the world remains challenging due to insufficient infrastructure. This research harnesses the power of computer vision technology and deep learning techniques to facilitate the early detection of crop diseases, thereby supporting the field of agriculture. The study employs computer vision technology and deep learning methods to assist in predicting crop diseases for agricultural purposes. Using a publicly available dataset containing 54,306 photos of both damaged and healthy plant leaves, a convolutional neural network (CNN) is trained. The validation data split is used to assess the model’s performance after it has been trained on the training set, by analyzing images of the leaves and comparing them with the dataset. The dataset encompasses various plant species in image format.