The paper aims to develop a system that creates recipes from food pictures using deep learning techniques. The proposed system will use a convolutional neural network to analyze the image and identify the ingredients, quantities, and cooking techniques used in the dish. Then, a natural language processing model will generate the recipe by mapping the ingredients and cooking techniques to a recipe template. The system will be trained on a huge dataset of recipe pictures and their corresponding recipes. The ultimate goal of this work is to create an intuitive and user-friendly tool for recipe generation that can be used by both professional chefs and home cooks. The system has the potential to revolutionize the way recipes are generated and shared, making it easier for people to experiment with new dishes and share their creations with others.