Abstract: With the improvement of people's living standards, consumers' demand for food quality and safety is growing. Traditional methods for detecting food quality and safety can no longer meet the demand for efficient, accurate and reliable detection. Therefore, it becomes imperative to seek a more efficient and convenient detection method. On this basis, the rapid development of deep neural network-based machine learning technology, i.e., deep learning, has brought new opportunities for food quality and safety detection. This paper focuses on the application progress of deep learning in food quality and safety detection. It introduces the principles of traditional machine learning and deep learning, and elaborates on the applications of deep learning in food origin tracing and food quality, including the detection of food defects, freshness, adulteration, and pathogens. Furthermore, it looks forward to the development trends of deep learning in the field of food quality and safety detection, aiming to provide theoretical references and research ideas for this field.