The human population has been increasing exponentially and is estimated that the total population will be at 8.6 billion by mid-2030. This tremendous rise in population will demand for an increase in the production as well as consumption of food. The major menace for security of food is the crop diseases that attack the agricultural produce during their growth. The rapid identification of the diseases that affect the crops remains difficult in different parts of the world due to the limited availability of infrastructure. To help in agriculture, this research uses computer vision technology and deep learning methods for assisting prediction of diseases of crops. A deep convolutional neural network (DNN) is trained on a public dataset of 54,306 images consisting of both diseased as well as healthy plant leaves. The model is trained on the train set and is validated using the validation split of data. The trained model has achieved an accuracy of 99.24% and can identify 14 crop species and 26 diseases. As a concrete deliverable of this research dCrop is made available as a smartphone app which is built using the trained disease prediction model. The farmer can capture the crop images using the app and analyze the presence or absence of diseases, thereby demonstrating the feasibility of the solution.