Leaf Tar Spot Detection Using RGB Images

TL;DR

This paper presents an automated method using Mask R-CNN for detecting tar spot disease on corn leaves from RGB images, enabling high-throughput and accurate disease quantification.

Contribution

The study introduces an automated ground truth generation process and demonstrates effective tar spot detection with Mask R-CNN on both leaf surface and in-field images.

Findings

Mask R-CNN accurately detects tar spots on leaf surfaces.

Automated ground truth generation reduces manual labeling effort.

Effective in-field detection of tar spot severity.

Abstract

Tar spot disease is a fungal disease that appears as a series of black circular spots containing spores on corn leaves. Tar spot has proven to be an impactful disease in terms of reducing crop yield. To quantify disease progression, experts usually have to visually phenotype leaves from the plant. This process is very time-consuming and is difficult to incorporate in any high-throughput phenotyping system. Deep neural networks could provide quick, automated tar spot detection with sufficient ground truth. However, manually labeling tar spots in images to serve as ground truth is also tedious and time-consuming. In this paper we first describe an approach that uses automated image analysis tools to generate ground truth images that are then used for training a Mask R-CNN. We show that a Mask R-CNN can be used effectively to detect tar spots in close-up images of leaf surfaces. We additionally show that the Mask R-CNN can also be used for in-field images of whole leaves to capture the number of tar spots and area of the leaf infected by the disease.