Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection

Post-harvest fruit grading is a necessary step to avoid disease related loss in quality. In this paper, hierarchical method proposed (1) remove the background and (2) detect images that contains grape diseases(botrytis, oidium, acid rot). Satisfying segmentation performances were obtained by Lite Unet model with 92.9% IoU score an average speed of 0.16s/image. A pretrained MobileNet-V2 94% F1 on classification. An optimized CNN reached 89% less than 10 times parameters. The implementation both classification models low-powered device would allow for real-time detection at press.