Sai Xu

Huazhong Lu

Xin Liang

The present disclosure discloses a non-destructive detection method and system forBradley, which includes: placing a lychee sample to be detected on a conveyor belt; acquiring sample information of the lychee sample based on visible/near-infrared light and X-ray imaging technology; wherein the visible/near-infrared light acquires internal quality features of the lychee sample; the X-ray imaging technology acquires internal density variation features of the lychee sample; analyzing the sample information according to a preset data processing and analysis method based on PLSR and a support vector machine to obtain a classification result of the lychee sample. The present disclosure uses the visible/near-infrared transmission spectrum and the X-ray imaging feature fusion in combination with PLSR to improve the detection accuracy of the lychee sample of the testing set to 92.92%, and in combination with the support vector regression to obtain a classification accuracy of 94.44% of the testing set.

Growing community of inventors

Guangdong, China

Sai Xu