LASSR: Effective Super-Resolution Method for Plant Disease Diagnosis

TL;DR

This paper introduces LASSR, a super-resolution technique tailored for plant disease diagnosis that effectively suppresses artifacts, resulting in higher quality images and significantly improved diagnostic performance over existing methods.

Contribution

LASSR is a novel artifact-suppression super-resolution method specifically designed for leaf disease diagnosis, outperforming ESRGAN in image quality and diagnostic accuracy.

Findings

LASSR-generated data boosts diagnosis accuracy by nearly 22%.

LASSR outperforms ESRGAN by over 2% in diagnostic tests.

LASSR produces higher quality images with fewer artifacts.

Abstract

The collection of high-resolution training data is crucial in building robust plant disease diagnosis systems, since such data have a significant impact on diagnostic performance. However, they are very difficult to obtain and are not always available in practice. Deep learning-based techniques, and particularly generative adversarial networks (GANs), can be applied to generate high-quality super-resolution images, but these methods often produce unexpected artifacts that can lower the diagnostic performance. In this paper, we propose a novel artifact-suppression super-resolution method that is specifically designed for diagnosing leaf disease, called Leaf Artifact-Suppression Super Resolution (LASSR). Thanks to its own artifact removal module that detects and suppresses artifacts to a considerable extent, LASSR can generate much more pleasing, high-quality images compared to the state-of-the-art ESRGAN model. Experiments based on a five-class cucumber disease (including healthy) discrimination model show that training with data generated by LASSR significantly boosts the performance on an unseen test dataset by nearly 22% compared with the baseline, and that our approach is more than 2% better than a model trained with images generated by ESRGAN.