Unsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method

Abstract Complicated image scene of the agricultural greenhouse plant images makes it very difficult to obtain precise manual labeling, leading to the hardship of getting the accurate training set of the conditional random field (CRF). Considering this problem, this paper proposed an unsupervised co...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ping Zhang, Lihong Xu
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2018
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/df18495121a34fe3b339323b7099a290
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:df18495121a34fe3b339323b7099a290
record_format	dspace
spelling	oai:doaj.org-article:df18495121a34fe3b339323b7099a2902021-12-02T15:08:24ZUnsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method10.1038/s41598-018-22568-32045-2322https://doaj.org/article/df18495121a34fe3b339323b7099a2902018-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-018-22568-3https://doaj.org/toc/2045-2322Abstract Complicated image scene of the agricultural greenhouse plant images makes it very difficult to obtain precise manual labeling, leading to the hardship of getting the accurate training set of the conditional random field (CRF). Considering this problem, this paper proposed an unsupervised conditional random field image segmentation algorithm ULCRF (Unsupervised Learning Conditional Random Field), which can perform fast unsupervised segmentation of greenhouse plant images, and further the plant organs in the image, i.e. fruits, leaves and stems, are segmented. The main idea of this algorithm is to calculate the unary potential, namely the initial label of the Dense CRF, by the unsupervised learning model LDA (Latent Dirichlet Allocation). In view of the ever-changing image features at different stages of fruit growth, a multi-resolution ULCRF is proposed to improve the accuracy of image segmentation in the middle stage and late stage of the fruit growth. An image is down-sampled twice to obtain three layers of different resolution images, and the features of each layer are interrelated with each other. Experiment results show that the proposed method can segment greenhouse plant images in an unsupervised method automatically and obtain a high segmentation accuracy together with a high extraction precision of the fruit part.Ping ZhangLihong XuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-13 (2018)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ping Zhang Lihong Xu Unsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method
description	Abstract Complicated image scene of the agricultural greenhouse plant images makes it very difficult to obtain precise manual labeling, leading to the hardship of getting the accurate training set of the conditional random field (CRF). Considering this problem, this paper proposed an unsupervised conditional random field image segmentation algorithm ULCRF (Unsupervised Learning Conditional Random Field), which can perform fast unsupervised segmentation of greenhouse plant images, and further the plant organs in the image, i.e. fruits, leaves and stems, are segmented. The main idea of this algorithm is to calculate the unary potential, namely the initial label of the Dense CRF, by the unsupervised learning model LDA (Latent Dirichlet Allocation). In view of the ever-changing image features at different stages of fruit growth, a multi-resolution ULCRF is proposed to improve the accuracy of image segmentation in the middle stage and late stage of the fruit growth. An image is down-sampled twice to obtain three layers of different resolution images, and the features of each layer are interrelated with each other. Experiment results show that the proposed method can segment greenhouse plant images in an unsupervised method automatically and obtain a high segmentation accuracy together with a high extraction precision of the fruit part.
format	article
author	Ping Zhang Lihong Xu
author_facet	Ping Zhang Lihong Xu
author_sort	Ping Zhang
title	Unsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method
title_short	Unsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method
title_full	Unsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method
title_fullStr	Unsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method
title_full_unstemmed	Unsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method
title_sort	unsupervised segmentation of greenhouse plant images based on statistical method
publisher	Nature Portfolio
publishDate	2018
url	https://doaj.org/article/df18495121a34fe3b339323b7099a290
work_keys_str_mv	AT pingzhang unsupervisedsegmentationofgreenhouseplantimagesbasedonstatisticalmethod AT lihongxu unsupervisedsegmentationofgreenhouseplantimagesbasedonstatisticalmethod
_version_	1718388155143421952

Unsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method

Ejemplares similares