With the increasing global demand for food consumption， food nondestructive detection technology has become increasingly important in food quality control and safety assurance. This paper systematically reviews the application and development trends of machine vision technology in food nondestructive detection. By analyzing current literature， various imaging technologies including RGB imaging， multispectral imaging， hyperspectral imaging， and Raman spectroscopy imaging， as well as detection algorithms such as traditional image processing， machine learning， and deep learning， are discussed in the context of food nondestructive detection. The paper also examines the technical challenges of machine vision in food nondestructive detection， such as the lack of datasets and the insufficient generalization ability of models in universal scenarios. Based on the current state of research， the paper envisions future research directions， proposing possible development paths such as multimodal data fusion， embedded detection systems， and close integration with deep learning technologies. This paper aims to provide a comprehensive research review for the development of food nondestructive detection technology and offer guidance and direction for technological innovation in practical applications.