Deep learning classification of desert-fringe vegetation patterns: Comparison of input layers

Deep Learning classification of nine imagery typologies (categories) of desert-fringe natural vegetation is performed using DenseNet with six input layer types: RGB, Red, Red CDF (Cumulative Distribution Function), Red Edge (variance), Combined (Red, CDF & Edge), and VARI (a measure of greenness). F1-score accuracy higher than 0.95 within 50 epochs was found for the RGB imagery. Red band and CDF alone showed only slightly lower performance. VARI representing 'net' color information facilitated very low separability between the nine pattern categories. However, combining Red, Red CDF and Red Edge allowed better classification than RGB, and a more stable increase in F1-scores was seen with the increase in the number of epochs. These results suggest that simple image morphological pre-processing may improve deep learning classification performance. Yet, these results are very preliminary and encourage the use of other mathematical morphology algorithms.

Automated summary

Deep learning classification of nine typologies of desert-fringe natural vegetation was performed using DenseNet with six input layer types. The results showed that the F1-score accuracy of the RGB imagery was higher than 0.95 within 50 epochs. Combining red, red CDF, and red edge allowed better classification than RGB and showed a more stable increase in F1-scores with the increase in the number of epochs. These preliminary results suggest that simple image morphological pre-processing can improve deep learning classification performance.