LASSR: Effective super-resolution method for plant disease diagnosis

•High-resolution training images were found to be particularly useful in the diagnosis of plant diseases.•Our super-resolution method (LASSR) generates significantly fewer artifacts than the previous state-of-the-art method.•Super-resolved images by LASSR can be used as reliable training resources.•LASSR largely improves the diagnostic accuracy by over 21% in average. 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 over 21% compared with the baseline, and that our approach is more than 2% better than a model trained with images generated by ESRGAN.