Enhancing Wheat Disease Diagnosis in a Greenhouse Using Image Deep Features and Parallel Feature Fusion

Zhao Zhang; Paulo Flores; Andrew Friskop; Zhaohui Liu; C Igathinathane; X Han; H J Kim; N Jahan; J Mathew; S Shreya

doi:10.3389/fpls.2022.834447

Enhancing Wheat Disease Diagnosis in a Greenhouse Using Image Deep Features and Parallel Feature Fusion

Front Plant Sci. 2022 Mar 10:13:834447. doi: 10.3389/fpls.2022.834447. eCollection 2022.

Authors

Zhao Zhang^{1

2}, Paulo Flores³, Andrew Friskop⁴, Zhaohui Liu⁴, C Igathinathane³, X Han^{5

6}, H J Kim^{6

7}, N Jahan³, J Mathew³, S Shreya⁸

Affiliations

¹ Key Laboratory of Modern Precision Agriculture System Integration Research, Ministry of Education, China Agricultural University, Beijing, China.
² Key Lab of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs, China Agricultural University, Beijing, China.
³ Department of Agricultural and Biosystems Engineering, North Dakota State University, Fargo, ND, United States.
⁴ Department of Plant Sciences, North Dakota State University, Fargo, ND, United States.
⁵ Department of Biosystems Engineering, College of Agriculture and Life Sciences, Kangwon National University, Chuncheon, South Korea.
⁶ Interdisciplinary Program in Smart Agriculture, College of Agriculture and Life Sciences, Kangwon National University, Chuncheon, South Korea.
⁷ Department of Biosystems and Biomaterials Engineering, College of Agriculture and Life Sciences, Seoul National University, Seoul, South Korea.
⁸ Department of Electrical and Computer Engineering, North Dakota State University, Fargo, ND, United States.

Abstract

Since the assessment of wheat diseases (e.g., leaf rust and tan spot) via visual observation is subjective and inefficient, this study focused on developing an automatic, objective, and efficient diagnosis approach. For each plant, color, and color-infrared (CIR) images were collected in a paired mode. An automatic approach based on the image processing technique was developed to crop the paired images to have the same region, after which a developed semiautomatic webtool was used to expedite the dataset creation. The webtool generated the dataset from either image and automatically built the corresponding dataset from the other image. Each image was manually categorized into one of the three groups: control (disease-free), disease light, and disease severity. After the image segmentation, handcrafted features (HFs) were extracted from each format of images, and disease diagnosis results demonstrated that the parallel feature fusion had higher accuracy over features from either type of image. Performance of deep features (DFs) extracted through different deep learning (DL) models (e.g., AlexNet, VGG16, ResNet101, GoogLeNet, and Xception) on wheat disease detection was compared, and those extracted by ResNet101 resulted in the highest accuracy, perhaps because deep layers extracted finer features. In addition, parallel deep feature fusion generated a higher accuracy over DFs from a single-source image. DFs outperformed HFs in wheat disease detection, and the DFs coupled with parallel feature fusion resulted in diagnosis accuracies of 75, 84, and 71% for leaf rust, tan spot, and leaf rust + tan spot, respectively. The methodology developed directly for greenhouse applications, to be used by plant pathologists, breeders, and other users, can be extended to field applications with future tests on field data and model fine-tuning.

Keywords: data fusion; deep features; handcrafted features; plant pathology; wheat disease.