Abstract: In fruit quality non-destructive testing, information derived from a single data source often falls short in providing a comprehensive representation of the subject under scrutiny, resulting in lower accuracy in detection. Integrating multiple data sources through data fusion allows for a more comprehensive information set, enhancing the precision of the assessment to a certain extent. Currently, data fusion techniques have been widely adopted in evaluating various aspects of fruits, holding promising prospects for further development. The article summarizes the methods, characteristics, and applications of data fusion in fruit assessment, and anticipates the future trends of this technology in the fruit detection domain by combining existing research findings.