Improved Recall of Plant Disease Detection Model using Image Super Resolution

Hyeonggyeong Kim, Chaesung Lim, Seungmin Tak

http://doi.org/10.5626/JOK.2024.51.2.125

Early identification and diagnosis of plant disease is very important because plant diseases have a great impact on yield. Currently, research on developing and advancing models for diagnosing plant diseases and pests using artificial intelligence is being actively conducted. However, even if the model showed good performance during verification, the performance deteriorates when the resolution of the input image is low during operation. If disease control is delayed because of delayed diseases diagnosis due to low resolution, the entire crop is affected by the diseases resulting in a decrease in yield. The purpose of this study was to improve the reproducibility of the model by utilizing super-resolution that increases the resolution of the image. BICUBIC, SRCNN, and SRGAN were used as super-resolution algorithms. After x4 scale super-resolution of test images with 64×64, 128×128, and 192×192 resolutions, they were directly input into the trained YOLOv5 model. As a result, the recall improved by 34% in SRGAN, 30% in SRCNN, and 19% in BICUBIC.