Evaluating Histogram Matching for Robust Deep learning-Based Grapevine Disease Detection
For plant disease detection in field conditions, this study offers a practical method to mitigate illumination variability, though the gains are incremental and domain-specific.
Histogram Matching (HM) is evaluated as a preprocessing and data augmentation technique to improve deep learning robustness against illumination variability in grapevine disease detection. On a dataset of 1,469 RGB images, combining HM for normalization and augmentation significantly enhanced classification accuracy on real-world canopy images, with the canopy subset showing marked improvement.
Variability in illumination is a primary factor limiting deep learning robustness for field-based plant disease detection. This study evaluates Histogram Matching (HM), a technique that transforms the pixel intensity distribution of an image to match a reference profile, to mitigate this in grapevine classification, distinguishing among healthy leaves, downy mildew, and spider mite damage. We propose a dual-stage integration of HM: (i) as a preprocessing step for normalization, and (ii) as a data augmentation technique to introduce controlled training variability. Experiments using 1,469 RGB images (comprising homogeneous leaf-focused and heterogeneous canopy samples) to train ResNet-18 models demonstrate that this combination significantly enhances robustness on real-world canopy images. While leaf-focused samples showed marginal gains, the canopy subset improved markedly, indicating that balancing normalization with histogram-based diversification effectively bridges the domain gap caused by uncontrolled lighting.