Fusion features of microfluorescence hyperspectral imaging for qualitative detection of pesticide residues in Hami melon.

Pesticide residues are identified as a significant food safety issue in Hami melons, and their rapid and accurate detection is deemed critical for ensuring public health. In response to the cumbersome procedures with existing chemical detection methods, this study explored the potential of identifying different pesticide residues in Hami melon by microfluorescence hyperspectral imaging (MF-HSI) technology combined with machine learning. By simulating the actual agricultural production, three pesticides, Beta-Cypermethrin, Difenoconazole, and Acetamiprid, were sprayed on Hami melons. The Hami melons with pesticide residues were collected as samples, from which spectral and image information were extracted. Competitive adaptive reweighted sampling (CARS), genetic algorithm (GA), and sequential projection algorithm (SPA) methods were used to extract characteristic wavelengths. Partial least squares discriminant analysis (PLS-DA), extreme learning machine (ELM), and k-nearest neighbor (KNN) classification models of the original spectra and characteristic wavelengths were established. 9 feature variables-Red (R), Green (G), Blue (B), Hue (H), Saturation (S), Value (V), Lightness (L), Red-Green axis (a) and Yellow-Blue axis (b) information was extracted by the color statistical method. 4 important color information of the image (G, B, V, L) were identified through Pearson correlation analysis, and the optimal feature wavelength was fused to enhance the identification accuracy of models. The results indicated that the SPA-PLS-DA model demonstrated the highest accuracy for the characteristic wavelength dataset, achieving accuracies of 89.35 % for the training set and 86.99 % for the testing set, which was better than the model established by the full wavelength dataset. Using the dataset that fuses feature wavelengths with 4 important image features, the SPA-PLS-DA model demonstrated superior performance, with recorded accuracy, precision, specificity, and sensitivity metrics on the testing set at 93.48 %, 93.81 %, 96.63 %, and 93.36 %, respectively. Consequently, MF-HSI technology combined with machine learning offers an approach to analyze pesticide residues in Hami melons accurately, and it provides a technical basis for detecting pesticide residues in other fruits and vegetables.