Abstract

Mycotoxin contamination by aflatoxin B1 (AFB1) and deoxynivalenol (DON) in maize silage threatens feed safety, requiring rapid, non-destructive monitoring tools. This study developed a visible-light machine vision approach combined with machine learning to quantify AFB1 and DON and classify contamination levels. A total of 210 silage samples were imaged, and 111 RGB-based color and texture features were extracted, followed by correlation analysis and model-based feature selection. Using the 10 selected features, support vector regression (SVR) achieved the best quantitative performance for AFB1 (R2 = 0.9945, RMSE = 3.18 µg·kg−1), while XGBoost performed best for DON (R2 = 0.9816, RMSE = 45.50 µg·kg−1). For classification, random forest and XGBoost correctly identified AFB1 contamination levels with an Accuracy of 90.48%, whereas SVM achieved 97.62% Accuracy for DON. Comparison of correlation-based and model-based feature importance confirmed the complementary value of statistically significant and nonlinearly predictive features. Biological interpretation suggested that color and texture responses may reflect fungal pigmentation/browning and multiscale surface-structure alterations, respectively, with selected texture descriptors changing earlier than color descriptors during aerobic exposure. The proposed low-cost RGB imaging strategy, coupled with multi-feature fusion, offers a promising approach for high-throughput preliminary mycotoxin screening in feed production.

IPC Classification

Keywords