DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection

In response to the difficulty of plant leaf disease detection and classification, this study proposes a novel plant leaf disease detection method called deep block attention SSD (DBA_SSD) for disease identification and disease degree classification of plant leaves. We propose three plant leaf detect...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jun Wang, Liya Yu, Jing Yang, Hao Dong
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	disease detection degree classification of disease data enhancement target recognition SSD Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/cfa37e92feb848a6849872755fc985e8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cfa37e92feb848a6849872755fc985e8
record_format	dspace
spelling	oai:doaj.org-article:cfa37e92feb848a6849872755fc985e82021-11-25T17:58:38ZDBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection10.3390/info121104742078-2489https://doaj.org/article/cfa37e92feb848a6849872755fc985e82021-11-01T00:00:00Zhttps://www.mdpi.com/2078-2489/12/11/474https://doaj.org/toc/2078-2489In response to the difficulty of plant leaf disease detection and classification, this study proposes a novel plant leaf disease detection method called deep block attention SSD (DBA_SSD) for disease identification and disease degree classification of plant leaves. We propose three plant leaf detection methods, namely, squeeze-and-excitation SSD (Se_SSD), deep block SSD (DB_SSD), and DBA_SSD. Se_SSD fuses SSD feature extraction network and attention mechanism channel, DB_SSD improves VGG feature extraction network, and DBA_SSD fuses the improved VGG network and channel attention mechanism. To reduce the training time and accelerate the training process, the convolutional layers trained in the Image Net image dataset by the VGG model are migrated to this model, whereas the collected plant leaves disease image dataset is randomly divided into training set, validation set, and test set in the ratio of 8:1:1. We chose the PlantVillage dataset after careful consideration because it contains images related to the domain of interest. This dataset consists of images of 14 plants, including images of apples, tomatoes, strawberries, peppers, and potatoes, as well as the leaves of other plants. In addition, data enhancement methods, such as histogram equalization and horizontal flip were used to expand the image data. The performance of the three improved algorithms is compared and analyzed in the same environment and with the classical target detection algorithms YOLOv4, YOLOv3, Faster RCNN, and YOLOv4 tiny. Experiments show that DBA_SSD outperforms the two other improved algorithms, and its performance in comparative analysis is superior to other target detection algorithms.Jun WangLiya YuJing YangHao DongMDPI AGarticledisease detectiondegree classification of diseasedata enhancementtarget recognitionSSDInformation technologyT58.5-58.64ENInformation, Vol 12, Iss 474, p 474 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	disease detection degree classification of disease data enhancement target recognition SSD Information technology T58.5-58.64
spellingShingle	disease detection degree classification of disease data enhancement target recognition SSD Information technology T58.5-58.64 Jun Wang Liya Yu Jing Yang Hao Dong DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection
description	In response to the difficulty of plant leaf disease detection and classification, this study proposes a novel plant leaf disease detection method called deep block attention SSD (DBA_SSD) for disease identification and disease degree classification of plant leaves. We propose three plant leaf detection methods, namely, squeeze-and-excitation SSD (Se_SSD), deep block SSD (DB_SSD), and DBA_SSD. Se_SSD fuses SSD feature extraction network and attention mechanism channel, DB_SSD improves VGG feature extraction network, and DBA_SSD fuses the improved VGG network and channel attention mechanism. To reduce the training time and accelerate the training process, the convolutional layers trained in the Image Net image dataset by the VGG model are migrated to this model, whereas the collected plant leaves disease image dataset is randomly divided into training set, validation set, and test set in the ratio of 8:1:1. We chose the PlantVillage dataset after careful consideration because it contains images related to the domain of interest. This dataset consists of images of 14 plants, including images of apples, tomatoes, strawberries, peppers, and potatoes, as well as the leaves of other plants. In addition, data enhancement methods, such as histogram equalization and horizontal flip were used to expand the image data. The performance of the three improved algorithms is compared and analyzed in the same environment and with the classical target detection algorithms YOLOv4, YOLOv3, Faster RCNN, and YOLOv4 tiny. Experiments show that DBA_SSD outperforms the two other improved algorithms, and its performance in comparative analysis is superior to other target detection algorithms.
format	article
author	Jun Wang Liya Yu Jing Yang Hao Dong
author_facet	Jun Wang Liya Yu Jing Yang Hao Dong
author_sort	Jun Wang
title	DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection
title_short	DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection
title_full	DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection
title_fullStr	DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection
title_full_unstemmed	DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection
title_sort	dba_ssd: a novel end-to-end object detection algorithm applied to plant disease detection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/cfa37e92feb848a6849872755fc985e8
work_keys_str_mv	AT junwang dbassdanovelendtoendobjectdetectionalgorithmappliedtoplantdiseasedetection AT liyayu dbassdanovelendtoendobjectdetectionalgorithmappliedtoplantdiseasedetection AT jingyang dbassdanovelendtoendobjectdetectionalgorithmappliedtoplantdiseasedetection AT haodong dbassdanovelendtoendobjectdetectionalgorithmappliedtoplantdiseasedetection
_version_	1718411770452770816

DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection

Ejemplares similares