Gray mold and anthracnose disease detection on strawberry leaves using hyperspectral imaging

Abstract

Abstract Background Gray mold and anthracnose are the main factors affecting strawberry quality and yield. Accurate and rapid early disease identification is of great significance to achieve precise targeted spraying to avoid large-scale spread of diseases and improve strawberry yield and quality. However, the characteristics between early disease infected leaves and healthy leaves are very similar, making the early identification of strawberry anthracnose and gray mold still challenging. Results Based on hyperspectral imaging technology, this study explored the potential of combining spectral fingerprint features and vegetation indices for early detection of strawberry leaf diseases. The CARS algorithm and ReliefF algorithm were used for the extraction of spectral fingerprint features and vegetation indices, respectively. Three machine learning models, BPNN, SVM and ELM, were developed for the early identification of strawberry anthracnose and gray mold, using spectral fingerprint features, vegetation index features and their combined features as inputs respectively. The results showed that the combination of spectral fingerprint features and vegetation index features had better recognition accuracy compared with individual features as inputs, and the accuracies of the three classifiers were 97.78%, 94.44%, and 93.33%, respectively. This indicates that the fused features approach proposed in this study can effectively improve the early detection performance of strawberry leaf diseases. Conclusions This study provides a basis for the development of a rapid online detection and real-time monitoring system for fruit diseases.