Quantifying the Severity of Common Rust in Maize Using Mask R-CNN

Pillay, Nelishia; Gerber, Mia; Holan, Katerina; Whitham, Steven A.; Berger, David Kenneth

doi:10.1007/978-3-030-87986-0_18

Cited by 11 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The image segmentation portion of this research focuses specifically on maize disease detection. This research utilizes three datasets: the Iowa State University maize disease dataset version one [47], the Iowa State University maize disease dataset Rp1d and the Iowa State University maize disease dataset Tilt. The three datasets will be referred to as ISU V1, ISU Rp1d and ISU Tilt, respectively, for the remainder of this research paper.…”

Section: Maize Disease Detectionmentioning

confidence: 99%

Automated Design of the Deep Neural Network Pipeline

Gerber

Pillay

2022

Applied Sciences

View full text Add to dashboard Cite

Deep neural networks have proven to be effective in various domains, especially in natural language processing and image processing. However, one of the challenges associated with using deep neural networks includes the long design time and expertise needed to apply these neural networks to a particular domain. The research presented in this paper investigates the automation of the design of the deep neural network pipeline to overcome this challenge. The deep learning pipeline includes identifying the preprocessing needed, the feature engineering technique, the neural network to use and the parameters for the neural network. A selection pertubative hyper-heuristic (SPHH) is used to automate the design pipeline. The study also examines the reusability of the generated pipeline. The effectiveness of transfer learning on the generated designs is also investigated. The proposed approach is evaluated for text processing—namely, sentiment analysis and spam detection—and image processing—namely, maize disease detection and oral lesion detection. The study revealed that the automated design of the deep neural network pipeline produces just as good, and in some cases better, performance compared to the manual design, with the automated design requiring less design time than the manual design. In the majority of instances, the design was not reusable; however, transfer learning achieved positive transfer of designs, with the performance being just as good or better than when transfer learning was not used.

show abstract

Section: Maize Disease Detectionmentioning

confidence: 99%

Automated Design of the Deep Neural Network Pipeline

Gerber

Pillay

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Field images of maize leaves with disease symptoms were thought to be good candidates for background removal since most images were made up of the main leaf in focus with different backgrounds. MaskRCNN has proven to be a useful tool for image segmentation [ 28 , 48 ]. In this study, it was adapted to produce a model called LeafRCNN which extracted maize leaves from their backgrounds.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Diagnostics of Gray Leaf Spot in Maize under Mixed Disease Field Conditions

Craze

Pillay

Joubert

et al. 2022

Plants

Self Cite

View full text Add to dashboard Cite

Maize yields worldwide are limited by foliar diseases that could be fungal, oomycete, bacterial, or viral in origin. Correct disease identification is critical for farmers to apply the correct control measures, such as fungicide sprays. Deep learning has the potential for automated disease classification from images of leaf symptoms. We aimed to develop a classifier to identify gray leaf spot (GLS) disease of maize in field images where mixed diseases were present (18,656 images after augmentation). In this study, we compare deep learning models trained on mixed disease field images with and without background subtraction. Performance was compared with models trained on PlantVillage images with single diseases and uniform backgrounds. First, we developed a modified VGG16 network referred to as “GLS_net” to perform binary classification of GLS, which achieved a 73.4% accuracy. Second, we used MaskRCNN to dynamically segment leaves from backgrounds in combination with GLS_net to identify GLS, resulting in a 72.6% accuracy. Models trained on PlantVillage images were 94.1% accurate at GLS classification with the PlantVillage testing set but performed poorly with the field image dataset (55.1% accuracy). In contrast, the GLS_net model was 78% accurate on the PlantVillage testing set. We conclude that deep learning models trained with realistic mixed disease field data obtain superior degrees of generalizability and external validity when compared to models trained using idealized datasets.

show abstract

“…In the original publication [1], Katerina Holan, who was involved in creating the ISU V1, ISU Rp1d and ISU Tilt datasets [2], was not acknowledged. After publication of the paper, the department requested that any use of the dataset acknowledge the person involved in creating the dataset.…”

mentioning

confidence: 99%

“…The authors would like to thank Katerina Holan for taking the photographs as well as partially annotating the images used in the ISU V1, ISU Rp1d and ISU Tilt datasets [2].…”

mentioning

confidence: 99%