Super-Resolution for Practical Automated Plant Disease Diagnosis System
This work addresses the practical issue of insufficient image resolution for automated plant disease diagnosis, which is incremental as it applies existing super-resolution techniques to a specific domain.
The paper tackles the problem of low-resolution images degrading automated plant disease diagnosis by proposing a super-resolution pre-processing method that improves classification accuracy by 26.9% over bicubic interpolation, achieving 92.5% accuracy compared to 95.5% with original high-resolution images.
Automated plant diagnosis using images taken from a distance is often insufficient in resolution and degrades diagnostic accuracy since the important external characteristics of symptoms are lost. In this paper, we first propose an effective pre-processing method for improving the performance of automated plant disease diagnosis systems using super-resolution techniques. We investigate the efficiency of two different super-resolution methods by comparing the disease diagnostic performance on the practical original high-resolution, low-resolution, and super-resolved cucumber images. Our method generates super-resolved images that look very close to natural images with 4$\times$ upscaling factors and is capable of recovering the lost detailed symptoms, largely boosting the diagnostic performance. Our model improves the disease classification accuracy by 26.9% over the bicubic interpolation method of 65.6% and shows a small gap (3% lower) between the original result of 95.5%.