A Fast and Automatic Method for Leaf Vein Network Extraction and Vein Density Measurement Based on Object-Oriented Classification
Rapidly determining leaf vein network patterns and vein densities is biologically important and technically challenging. Current methods, however, are limited to vein contour extraction. Further image processing is difficult, and some leaf vein traits of interest therefore cannot be quantified. In t...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-05-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fpls.2020.00499/full |
| _version_ | 1828750206891458560 |
|---|---|
| author | Jiyou Zhu Jiangming Yao Qiang Yu Weijun He Weijun He Chengyang Xu Guoming Qin Qiuyu Zhu Dayong Fan Hua Zhu |
| author_facet | Jiyou Zhu Jiangming Yao Qiang Yu Weijun He Weijun He Chengyang Xu Guoming Qin Qiuyu Zhu Dayong Fan Hua Zhu |
| author_sort | Jiyou Zhu |
| collection | DOAJ |
| description | Rapidly determining leaf vein network patterns and vein densities is biologically important and technically challenging. Current methods, however, are limited to vein contour extraction. Further image processing is difficult, and some leaf vein traits of interest therefore cannot be quantified. In this study, we proposed a novel method for the fast and accurate determination of leaf vein network patterns and vein density. Nine tree species with different leaf characteristics and vein types were applied to verify this method. To overcome the image processing difficulties at the microscopic scale, we adopted the remote object-oriented classification method applied comprehensively in the field of remote sensing research. The key to this approach is to determine the universally applicable leaf vein extraction threshold values (scale parameter, shape parameter, compactness parameter, brightness feature, spectral feature and geometric feature). Based on our analysis, the following recommended threshold values were determined: the scale parameter was 250, the shape parameter was 0.7, the compactness parameter was 0.3, the brightness feature value was 230∼280, the spectral feature value was 180∼230, and the geometric feature value was less than 2. With the optimal extraction parameters applied, the extraction precision was above 96.40% on average for the nine species studied. The leaf vein density calculation rate increased by more than 87.3% compared to that of the traditional methods. The results showed that this method is accurate, fast, flexible and complementary to existing technologies. It is an effective tool for the fast extraction of vein networks and the exploration of leaf vein characteristics, particularly for large-scale studies in plant vein physiology. |
| first_indexed | 2024-12-10T20:34:48Z |
| format | Article |
| id | doaj.art-8bc35b3898e14bc8847dacd37817de74 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-12-10T20:34:48Z |
| publishDate | 2020-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-8bc35b3898e14bc8847dacd37817de742022-12-22T01:34:35ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2020-05-011110.3389/fpls.2020.00499465886A Fast and Automatic Method for Leaf Vein Network Extraction and Vein Density Measurement Based on Object-Oriented ClassificationJiyou Zhu0Jiangming Yao1Qiang Yu2Weijun He3Weijun He4Chengyang Xu5Guoming Qin6Qiuyu Zhu7Dayong Fan8Hua Zhu9Key Laboratory for Silviculture and Conservation of Ministry of Education, Key Laboratory for Silviculture and Forest Ecosystem of State Forestry Administration, Research Center for Urban Forestry, Beijing Forestry University, Beijing, ChinaForestry College, Guangxi University, Nanning, ChinaKey Laboratory for Silviculture and Conservation of Ministry of Education, Key Laboratory for Silviculture and Forest Ecosystem of State Forestry Administration, Research Center for Urban Forestry, Beijing Forestry University, Beijing, ChinaForestry College, Guangxi University, Nanning, ChinaResearch Institute of Tropical Forestry, Chinese Academy of Forestry, Guangzhou, ChinaKey Laboratory for Silviculture and Conservation of Ministry of Education, Key Laboratory for Silviculture and Forest Ecosystem of State Forestry Administration, Research Center for Urban Forestry, Beijing Forestry University, Beijing, ChinaResearch Institute of Tropical Forestry, Chinese Academy of Forestry, Guangzhou, ChinaInspection Department of Guangxi Medical College, Nanning, ChinaKey Laboratory for Silviculture and Conservation of Ministry of Education, Key Laboratory for Silviculture and Forest Ecosystem of State Forestry Administration, Research Center for Urban Forestry, Beijing Forestry University, Beijing, ChinaInspection Department of Guangxi Medical College, Nanning, ChinaRapidly determining leaf vein network patterns and vein densities is biologically important and technically challenging. Current methods, however, are limited to vein contour extraction. Further image processing is difficult, and some leaf vein traits of interest therefore cannot be quantified. In this study, we proposed a novel method for the fast and accurate determination of leaf vein network patterns and vein density. Nine tree species with different leaf characteristics and vein types were applied to verify this method. To overcome the image processing difficulties at the microscopic scale, we adopted the remote object-oriented classification method applied comprehensively in the field of remote sensing research. The key to this approach is to determine the universally applicable leaf vein extraction threshold values (scale parameter, shape parameter, compactness parameter, brightness feature, spectral feature and geometric feature). Based on our analysis, the following recommended threshold values were determined: the scale parameter was 250, the shape parameter was 0.7, the compactness parameter was 0.3, the brightness feature value was 230∼280, the spectral feature value was 180∼230, and the geometric feature value was less than 2. With the optimal extraction parameters applied, the extraction precision was above 96.40% on average for the nine species studied. The leaf vein density calculation rate increased by more than 87.3% compared to that of the traditional methods. The results showed that this method is accurate, fast, flexible and complementary to existing technologies. It is an effective tool for the fast extraction of vein networks and the exploration of leaf vein characteristics, particularly for large-scale studies in plant vein physiology.https://www.frontiersin.org/article/10.3389/fpls.2020.00499/fullleaf vein networkleaf vein densityobject-oriented methodremote sensingextraction |
| spellingShingle | Jiyou Zhu Jiangming Yao Qiang Yu Weijun He Weijun He Chengyang Xu Guoming Qin Qiuyu Zhu Dayong Fan Hua Zhu A Fast and Automatic Method for Leaf Vein Network Extraction and Vein Density Measurement Based on Object-Oriented Classification Frontiers in Plant Science leaf vein network leaf vein density object-oriented method remote sensing extraction |
| title | A Fast and Automatic Method for Leaf Vein Network Extraction and Vein Density Measurement Based on Object-Oriented Classification |
| title_full | A Fast and Automatic Method for Leaf Vein Network Extraction and Vein Density Measurement Based on Object-Oriented Classification |
| title_fullStr | A Fast and Automatic Method for Leaf Vein Network Extraction and Vein Density Measurement Based on Object-Oriented Classification |
| title_full_unstemmed | A Fast and Automatic Method for Leaf Vein Network Extraction and Vein Density Measurement Based on Object-Oriented Classification |
| title_short | A Fast and Automatic Method for Leaf Vein Network Extraction and Vein Density Measurement Based on Object-Oriented Classification |
| title_sort | fast and automatic method for leaf vein network extraction and vein density measurement based on object oriented classification |
| topic | leaf vein network leaf vein density object-oriented method remote sensing extraction |
| url | https://www.frontiersin.org/article/10.3389/fpls.2020.00499/full |
| work_keys_str_mv | AT jiyouzhu afastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT jiangmingyao afastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT qiangyu afastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT weijunhe afastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT weijunhe afastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT chengyangxu afastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT guomingqin afastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT qiuyuzhu afastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT dayongfan afastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT huazhu afastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT jiyouzhu fastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT jiangmingyao fastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT qiangyu fastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT weijunhe fastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT weijunhe fastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT chengyangxu fastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT guomingqin fastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT qiuyuzhu fastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT dayongfan fastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification AT huazhu fastandautomaticmethodforleafveinnetworkextractionandveindensitymeasurementbasedonobjectorientedclassification |