Food is necessary for human existence, and people are always trying out new, tasty dishes. People frequently select food products from grocery stores that they don't even know the names of or that they don't immediately recognise. It's crucial to understand which elements may be combined to create delicious cuisine recipes. For a beginner chef, picking the proper recipe from a list of items is really challenging. Even for specialists, it may be a challenge. Machine learning is constantly being used in our daily lives. One such instance is object recognition using image processing. Even though there are many different food items involved in this procedure, traditional methods will result in a higher risk of error. ingredients. Deep learning and machine learning techniques can be used to overcome these issues. In this research, we constructed a model for identifying food ingredients and created an algorithm for recipe recommendation based on identified ingredients. We created a unique dataset with 9856 photos divided into 32 types of food items. We used a Convolution Neural Network (CNN) model to recognise food items, and machine learning to generate recipes. We had a 94% accuracy rate, which is extremely helpful.