Automatic Evaluation of Wheat Resistance to Fusarium Head Blight Using Dual Mask-RCNN Deep Learning Frameworks in Computer Vision

Abstract

In many regions of the world, wheat is vulnerable to severe yield and quality losses from the fungus disease of Fusarium head blight (FHB). The development of resistant cultivars is one means of ameliorating the devastating effects of this disease, but the breeding process requires the evaluation of hundreds of lines each year for reaction to the disease. These field evaluations are laborious, expensive, time-consuming, and are prone to rater error. A phenotyping cart that can quickly capture images of the spikes of wheat lines and their level of FHB infection would greatly benefit wheat breeding programs. In this study, mask region convolutional neural network (Mask-RCNN) allowed for reliable identification of the symptom location and the disease severity of wheat spikes. Within a wheat line planted in the field, color images of individual wheat spikes and their corresponding diseased areas were labeled and segmented into sub-images. Images with annotated spikes and sub-images of individual spikes with labeled diseased areas were used as ground truth data to train Mask-RCNN models for automatic image segmentation of wheat spikes and FHB diseased areas, respectively. The feature pyramid network (FPN) based on ResNet-101 network was used as the backbone of Mask-RCNN for constructing the feature pyramid and extracting features. After generating mask images of wheat spikes from full-size images, Mask-RCNN was performed to predict diseased areas on each individual spike. This protocol enabled the rapid recognition of wheat spikes and diseased areas with the detection rates of 77.76% and 98.81%, respectively. The prediction accuracy of 77.19% was achieved by calculating the ratio of the wheat FHB severity value of prediction over ground truth. This study demonstrates the feasibility of rapidly determining levels of FHB in wheat spikes, which will greatly facilitate the breeding of resistant cultivars.

Imaging Spectroscopy and Machine Learning for Intelligent Determination of Potato and Sweet Potato Quality

“…The training data set is better to be large enough to prevent overfitting. The acquisition of large data sets often requires a large number of images to be annotated, which is a high labor cost [ 135 ].…”

DeepCob: precise and high-throughput analysis of maize cob geometry using deep learning with an application in genebank phenomics

“…Our comparison of three image segmentation methods showed Mask R-CNN to be superior to the classic image analysis method Felzenszwalb-Huttenlocher segmentation and Window-CNN for maize cob detection and segmentation. Given the recent success of Mask R-CNN for image segmentation in medicine or robotics, its application for plant phenotyping is highly promising as demonstrated in strawberry fruit detection for harvesting robots [ 72 ], orange fruit detection [ 18 ], pomegranate tree detection [ 73 ], disease monitoring in wheat [ 59 ], and seed analysis in rice and soybean [ 30 , 71 ]. Here we present another application of Mask R-CNN for maize cob instance segmentation and quantitative phenotyping in the context of genebank phenomics.…”

Tennis Robot Design via Internet of Things and Deep Learning

“…The network is easily extended to other tasks, such as estimating a person's posture, that is, detecting a person's key points. The framework includes instance segmentation, candidate frame object detection, and person key point detection [26]. Its structure is shown in Figure 1.…”