Impacts of Background Removal on Convolutional Neural Networks for Plant Disease Classification In-Situ

Kamal Kc, Zhendong Yin, Dasen Li and Zhilu Wu
Additional contact information
Kamal Kc: School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China
Zhendong Yin: School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China
Dasen Li: School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China
Zhilu Wu: School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China

Agriculture, 2021, vol. 11, issue 9, 1-16

Abstract: Convolutional neural networks have an immense impact on computer vision tasks. However, the accuracy of convolutional neural networks on a dataset is tremendously affected when images within the dataset highly vary. Test images of plant leaves are usually taken in situ. These images, apart from the region of interest, contain unwanted parts of plants, soil, rocks, and/or human body parts. Segmentation helps isolate the target region and a deep convolutional neural network classifies images precisely. Therefore, we combined edge and morphological based segmentation, background subtraction, and the convolutional neural network to help improve accuracy on image sets with images containing clean and cluttered backgrounds. In the proposed system, segmentation was applied to first extract leaf images in the foreground. Several images contained a leaf of interest interposed between unfavorable foregrounds and backgrounds. Background subtraction was implemented to remove the foreground image followed by segmentation to obtain the region of interest. Finally, the images were classified by a pre-trained classification network. The experimental results on two, four, and eight classes of datasets show that the proposed method achieves 98.7%, 96.7%, and 93.57% accuracy by fine-tuned DenseNet121, InceptionV3, and DenseNet121 models, respectively, on a clean dataset. For two class datasets, the accuracy obtained was about 12% higher for a dataset with images taken in the homogeneous background compared to that of a dataset with testing images with a cluttered background. Results also suggest that image sets with clean backgrounds tend to start training with higher accuracy and converge faster.

Keywords: segmentation; background subtraction; transfer learning; deep convolutional neural network; plant disease image classification (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2021
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2077-0472/11/9/827/pdf (application/pdf)
https://www.mdpi.com/2077-0472/11/9/827/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:11:y:2021:i:9:p:827-:d:625657

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().