Plant leaf detection using modified active shape models

CORC > 烟台海岸带研究所 > 中国科学院烟台海岸带研究所 > 山东省海岸带环境工程技术研究中心

	Plant leaf detection using modified active shape models
	Xia, Chunlei1,2,5 ; Lee, Jang-Myung 1; Li, Yan 1; Song, Yoo-Han 3; Chung, Bu-Keun 4; Chon, Tae-Soo 2
刊名	BIOSYSTEMS ENGINEERING
	2013-09-01
卷号	116 期号:1 页码:23-35
关键词	RECOGNITION CLASSIFICATION SEGMENTATION IDENTIFICATION ALGORITHM FEATURES IMAGES
ISSN号	1537-5110
其他题名	SERS-based immunoassay of tumor marker VEGF using DNA aptamers and silica-encapsulated hollow gold nanospheres.pdf
通讯作者	Chon, TS (reprint author), Pusan Natl Univ, Dept Biol Sci, Pusan 609735, South Korea. tschon@pusan.ac.kr
产权排序	[Xia, Chunlei; Lee, Jang-Myung; Li, Yan] Pusan Natl Univ, Sch Elect Engn, Pusan 609735, South Korea; [Xia, Chunlei; Chon, Tae-Soo] Pusan Natl Univ, Dept Biol Sci, Pusan 609735, South Korea; [Song, Yoo-Han] Gyeongsang Natl Univ, Dept Appl Biol & Environm Sci, Jinju, South Korea; [Chung, Bu-Keun] Gyeongnam Agr Res & Extens Serv, Div Plant Environm, Jinju, South Korea; [Xia, Chunlei] Chinese Acad Sci, Yantai Inst Coastal Zone Res, Yantai 264003, Peoples R China
中文摘要	We propose an in situ detection method of multiple leaves with overlapping and occlusion in greenhouse conditions. Initially a multilayer perceptron (MLP) is used to classify partial boundary images of pepper leaves. After the partial leaf boundary detection, active shape models (ASMs) are subsequently built to employ the images of entire leaves based on a priori knowledge using landmark. Two deformable models were developed with pepper leaves: Boundary-ASM and MLP-ASM. Matching processes are carried out by deforming the trained leaf models to fit real leaf images collected in the greenhouse. MLP-ASM detected 76.7 and 87.8% of overlapping and occluded pepper leaves respectively, while Boundary-ASM showed detection rates of 63.4 and 76.7%. The detection rates by the conventional ASM were 23.3 and 29.3%. The leaf models trained with pepper leaves were further tested with leaves of paprika, in the same family but with more complex shapes (e.g., holes and rolling). Although the overall detection rates were somewhat lower than those for pepper, the rates for the occluded and overlapping leaves of paprika were still higher with MLP-ASM (ranging from 60.4 to 76.7%) and Boundary-ASM (ranging from 50.5 to 63.3%) than using the conventional active shape model (from 21.6 to 30.0%). The modified active shape models with the boundary classifier could be an efficient means for detecting multiple leaves in field conditions. (c) 2013 IAgrE. Published by Elsevier Ltd. All rights reserved.
英文摘要	We propose an in situ detection method of multiple leaves with overlapping and occlusion in greenhouse conditions. Initially a multilayer perceptron (MLP) is used to classify partial boundary images of pepper leaves. After the partial leaf boundary detection, active shape models (ASMs) are subsequently built to employ the images of entire leaves based on a priori knowledge using landmark. Two deformable models were developed with pepper leaves: Boundary-ASM and MLP-ASM. Matching processes are carried out by deforming the trained leaf models to fit real leaf images collected in the greenhouse. MLP-ASM detected 76.7 and 87.8% of overlapping and occluded pepper leaves respectively, while Boundary-ASM showed detection rates of 63.4 and 76.7%. The detection rates by the conventional ASM were 23.3 and 29.3%. The leaf models trained with pepper leaves were further tested with leaves of paprika, in the same family but with more complex shapes (e.g., holes and rolling). Although the overall detection rates were somewhat lower than those for pepper, the rates for the occluded and overlapping leaves of paprika were still higher with MLP-ASM (ranging from 60.4 to 76.7%) and Boundary-ASM (ranging from 50.5 to 63.3%) than using the conventional active shape model (from 21.6 to 30.0%). The modified active shape models with the boundary classifier could be an efficient means for detecting multiple leaves in field conditions. (c) 2013 IAgrE. Published by Elsevier Ltd. All rights reserved.
学科主题	Agricultural Engineering ; Agriculture, Multidisciplinary
研究领域[WOS]	Agriculture
关键词[WOS]	RECOGNITION ; CLASSIFICATION ; SEGMENTATION ; IDENTIFICATION ; ALGORITHM ; FEATURES ; IMAGES
收录类别	SCI
资助信息	Korea Institute of Planning and Evaluation for Technology of Food, Agriculture, Forestry, and Fisheries [108929033HD120]
原文出处	http://dx.doi.org/10.1016/j.biosystemseng.2013.06.003
语种	英语
WOS记录号	WOS:000323856000003
公开日期	2014-07-08
内容类型	期刊论文
源URL	[http://ir.yic.ac.cn/handle/133337/7055]
专题	烟台海岸带研究所_山东省海岸带环境工程技术研究中心烟台海岸带研究所_海岸带生物学与生物资源利用所重点实验室烟台海岸带研究所_中科院海岸带环境过程与生态修复重点实验室
作者单位	1.Pusan Natl Univ, Sch Elect Engn, Pusan 609735, South Korea 2.Pusan Natl Univ, Dept Biol Sci, Pusan 609735, South Korea 3.Gyeongsang Natl Univ, Dept Appl Biol & Environm Sci, Jinju, South Korea 4.Gyeongnam Agr Res & Extens Serv, Div Plant Environm, Jinju, South Korea 5.Chinese Acad Sci, Yantai Inst Coastal Zone Res, Yantai 264003, Peoples R China
推荐引用方式 GB/T 7714	Xia, Chunlei,Lee, Jang-Myung,Li, Yan,et al. Plant leaf detection using modified active shape models[J]. BIOSYSTEMS ENGINEERING,2013,116(1):23-35.
APA	Xia, Chunlei,Lee, Jang-Myung,Li, Yan,Song, Yoo-Han,Chung, Bu-Keun,&Chon, Tae-Soo.(2013).Plant leaf detection using modified active shape models.BIOSYSTEMS ENGINEERING,116(1),23-35.
MLA	Xia, Chunlei,et al."Plant leaf detection using modified active shape models".BIOSYSTEMS ENGINEERING 116.1(2013):23-35.