A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds
This study investigated the possibility of using visible and near-infrared (VIS/NIR) hyperspectral imaging techniques to discriminate viable and non-viable wheat seeds. Both sides of individual seeds were subjected to hyperspectral imaging (400–1000 nm) to acquire reflectance spectral data. Four spe...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/3/813 |
| _version_ | 1828283882070343680 |
|---|---|
| author | Tingting Zhang Wensong Wei Bin Zhao Ranran Wang Mingliu Li Liming Yang Jianhua Wang Qun Sun |
| author_facet | Tingting Zhang Wensong Wei Bin Zhao Ranran Wang Mingliu Li Liming Yang Jianhua Wang Qun Sun |
| author_sort | Tingting Zhang |
| collection | DOAJ |
| description | This study investigated the possibility of using visible and near-infrared (VIS/NIR) hyperspectral imaging techniques to discriminate viable and non-viable wheat seeds. Both sides of individual seeds were subjected to hyperspectral imaging (400–1000 nm) to acquire reflectance spectral data. Four spectral datasets, including the ventral groove side, reverse side, mean (the mean of two sides’ spectra of every seed), and mixture datasets (two sides’ spectra of every seed), were used to construct the models. Classification models, partial least squares discriminant analysis (PLS-DA), and support vector machines (SVM), coupled with some pre-processing methods and successive projections algorithm (SPA), were built for the identification of viable and non-viable seeds. Our results showed that the standard normal variate (SNV)-SPA-PLS-DA model had high classification accuracy for whole seeds (>85.2%) and for viable seeds (>89.5%), and that the prediction set was based on a mixed spectral dataset by only using 16 wavebands. After screening with this model, the final germination of the seed lot could be higher than 89.5%. Here, we develop a reliable methodology for predicting the viability of wheat seeds, showing that the VIS/NIR hyperspectral imaging is an accurate technique for the classification of viable and non-viable wheat seeds in a non-destructive manner. |
| first_indexed | 2024-04-13T08:52:47Z |
| format | Article |
| id | doaj.art-feaa2de2de964f449c0a54edc03bc684 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T08:52:47Z |
| publishDate | 2018-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-feaa2de2de964f449c0a54edc03bc6842022-12-22T02:53:26ZengMDPI AGSensors1424-82202018-03-0118381310.3390/s18030813s18030813A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat SeedsTingting Zhang0Wensong Wei1Bin Zhao2Ranran Wang3Mingliu Li4Liming Yang5Jianhua Wang6Qun Sun7Department of Plant Genetics and Breeding, College of Agriculture, China Agricultural University/Beijing Key Laboratory of Crop Genetic Improvement/The Innovation Center (Beijing) of Crop Seed Sciences Ministry of Agriculture, Beijing 100193, ChinaNational R&D Center for Agro-Processing Equipments, College of Engineering, China Agricultural University, Beijing 100083, ChinaDepartment of Plant Genetics and Breeding, College of Agriculture, China Agricultural University/Beijing Key Laboratory of Crop Genetic Improvement/The Innovation Center (Beijing) of Crop Seed Sciences Ministry of Agriculture, Beijing 100193, ChinaDepartment of Plant Genetics and Breeding, College of Agriculture, China Agricultural University/Beijing Key Laboratory of Crop Genetic Improvement/The Innovation Center (Beijing) of Crop Seed Sciences Ministry of Agriculture, Beijing 100193, ChinaDepartment of Plant Genetics and Breeding, College of Agriculture, China Agricultural University/Beijing Key Laboratory of Crop Genetic Improvement/The Innovation Center (Beijing) of Crop Seed Sciences Ministry of Agriculture, Beijing 100193, ChinaCollege of Science, China Agricultural University, Beijing 100083, ChinaDepartment of Plant Genetics and Breeding, College of Agriculture, China Agricultural University/Beijing Key Laboratory of Crop Genetic Improvement/The Innovation Center (Beijing) of Crop Seed Sciences Ministry of Agriculture, Beijing 100193, ChinaDepartment of Plant Genetics and Breeding, College of Agriculture, China Agricultural University/Beijing Key Laboratory of Crop Genetic Improvement/The Innovation Center (Beijing) of Crop Seed Sciences Ministry of Agriculture, Beijing 100193, ChinaThis study investigated the possibility of using visible and near-infrared (VIS/NIR) hyperspectral imaging techniques to discriminate viable and non-viable wheat seeds. Both sides of individual seeds were subjected to hyperspectral imaging (400–1000 nm) to acquire reflectance spectral data. Four spectral datasets, including the ventral groove side, reverse side, mean (the mean of two sides’ spectra of every seed), and mixture datasets (two sides’ spectra of every seed), were used to construct the models. Classification models, partial least squares discriminant analysis (PLS-DA), and support vector machines (SVM), coupled with some pre-processing methods and successive projections algorithm (SPA), were built for the identification of viable and non-viable seeds. Our results showed that the standard normal variate (SNV)-SPA-PLS-DA model had high classification accuracy for whole seeds (>85.2%) and for viable seeds (>89.5%), and that the prediction set was based on a mixed spectral dataset by only using 16 wavebands. After screening with this model, the final germination of the seed lot could be higher than 89.5%. Here, we develop a reliable methodology for predicting the viability of wheat seeds, showing that the VIS/NIR hyperspectral imaging is an accurate technique for the classification of viable and non-viable wheat seeds in a non-destructive manner.http://www.mdpi.com/1424-8220/18/3/813hyperspectral imagingseed viabilitydatasetPLS-DASVM |
| spellingShingle | Tingting Zhang Wensong Wei Bin Zhao Ranran Wang Mingliu Li Liming Yang Jianhua Wang Qun Sun A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds Sensors hyperspectral imaging seed viability dataset PLS-DA SVM |
| title | A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds |
| title_full | A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds |
| title_fullStr | A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds |
| title_full_unstemmed | A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds |
| title_short | A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds |
| title_sort | reliable methodology for determining seed viability by using hyperspectral data from two sides of wheat seeds |
| topic | hyperspectral imaging seed viability dataset PLS-DA SVM |
| url | http://www.mdpi.com/1424-8220/18/3/813 |
| work_keys_str_mv | AT tingtingzhang areliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT wensongwei areliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT binzhao areliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT ranranwang areliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT mingliuli areliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT limingyang areliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT jianhuawang areliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT qunsun areliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT tingtingzhang reliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT wensongwei reliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT binzhao reliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT ranranwang reliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT mingliuli reliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT limingyang reliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT jianhuawang reliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds AT qunsun reliablemethodologyfordeterminingseedviabilitybyusinghyperspectraldatafromtwosidesofwheatseeds |