Abstract: Tomatoes are one of the most widely cultivated vegetables in China and are popular among consumers. In recent years, as the demand for healthy food has grown, the quality of tomatoes has aroused increasing attention. While tomatoes are generally uniform in shape, there are significant differences in size, fruit type and color among tomato varieties, and tomatoes contain a variety of nutrients with complex chemical structures, so its quality is difficult to assess. The traditional tomato quality testing methods are subjective, destructive, time-consuming and laborious, and thus cannot meet the demand of large-scale quality testing. Recently, with the development of non-destructive testing technologies, new detection methods such as machine learning, multispectral techniques, and electronic nose/electronic tongue have been developed and applied for the rapid and non-destructive testing of tomato quality. This paper provides a summary of the development and application of artificial intelligence based on image recognition, electronic nose technology and spectroscopic technologies for the non-destructive testing of tomatoes in order to provide a reference for future research and development of tomato quality inspection.

Key words: tomato quality inspection; visible-near infrared spectroscopy; hyperspectral imaging; Raman spectroscopy; electronic nose; machine vision