HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds
High-throughput, nondestructive, and precise measurement of seeds is critical for the evaluation of seed quality and the improvement of agricultural productions. To this end, we have developed a novel end-to-end platform named <i>HyperSeed</i> to provide hyperspectral information for see...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/24/8184 |
| _version_ | 1797500853251211264 |
|---|---|
| author | Tian Gao Anil Kumar Nalini Chandran Puneet Paul Harkamal Walia Hongfeng Yu |
| author_facet | Tian Gao Anil Kumar Nalini Chandran Puneet Paul Harkamal Walia Hongfeng Yu |
| author_sort | Tian Gao |
| collection | DOAJ |
| description | High-throughput, nondestructive, and precise measurement of seeds is critical for the evaluation of seed quality and the improvement of agricultural productions. To this end, we have developed a novel end-to-end platform named <i>HyperSeed</i> to provide hyperspectral information for seeds. As a test case, the hyperspectral images of rice seeds are obtained from a high-performance line-scan image spectrograph covering the spectral range from 600 to 1700 nm. The acquired images are processed via a graphical user interface (GUI)-based open-source software for background removal and seed segmentation. The output is generated in the form of a hyperspectral cube and curve for each seed. In our experiment, we presented the visual results of seed segmentation on different seed species. Moreover, we conducted a classification of seeds raised in heat stress and control environments using both traditional machine learning models and neural network models. The results show that the proposed 3D convolutional neural network (3D CNN) model has the highest accuracy, which is 97.5% in seed-based classification and 94.21% in pixel-based classification, compared to 80.0% in seed-based classification and 85.67% in seed-based classification from the support vector machine (SVM) model. Moreover, our pipeline enables systematic analysis of spectral curves and identification of wavelengths of biological interest. |
| first_indexed | 2024-03-10T03:09:50Z |
| format | Article |
| id | doaj.art-8e314b1a6bd8419d8e3c240f4eae51f0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:09:50Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8e314b1a6bd8419d8e3c240f4eae51f02023-11-23T10:28:02ZengMDPI AGSensors1424-82202021-12-012124818410.3390/s21248184HyperSeed: An End-to-End Method to Process Hyperspectral Images of SeedsTian Gao0Anil Kumar Nalini Chandran1Puneet Paul2Harkamal Walia3Hongfeng Yu4School of Computing, University of Nebraska-Lincoln, Lincoln, NE 68588, USADepartment of Agronomy and Horticulture, University of Nebraska-Lincoln, Lincoln, NE 68583, USADepartment of Agronomy and Horticulture, University of Nebraska-Lincoln, Lincoln, NE 68583, USADepartment of Agronomy and Horticulture, University of Nebraska-Lincoln, Lincoln, NE 68583, USASchool of Computing, University of Nebraska-Lincoln, Lincoln, NE 68588, USAHigh-throughput, nondestructive, and precise measurement of seeds is critical for the evaluation of seed quality and the improvement of agricultural productions. To this end, we have developed a novel end-to-end platform named <i>HyperSeed</i> to provide hyperspectral information for seeds. As a test case, the hyperspectral images of rice seeds are obtained from a high-performance line-scan image spectrograph covering the spectral range from 600 to 1700 nm. The acquired images are processed via a graphical user interface (GUI)-based open-source software for background removal and seed segmentation. The output is generated in the form of a hyperspectral cube and curve for each seed. In our experiment, we presented the visual results of seed segmentation on different seed species. Moreover, we conducted a classification of seeds raised in heat stress and control environments using both traditional machine learning models and neural network models. The results show that the proposed 3D convolutional neural network (3D CNN) model has the highest accuracy, which is 97.5% in seed-based classification and 94.21% in pixel-based classification, compared to 80.0% in seed-based classification and 85.67% in seed-based classification from the support vector machine (SVM) model. Moreover, our pipeline enables systematic analysis of spectral curves and identification of wavelengths of biological interest.https://www.mdpi.com/1424-8220/21/24/8184hyperspectral imaging systemhigh-throughput seed phenotypingphenotyping softwareseed heat stress3D convolutional neural network (CNN)support vector machine (SVM) |
| spellingShingle | Tian Gao Anil Kumar Nalini Chandran Puneet Paul Harkamal Walia Hongfeng Yu HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds Sensors hyperspectral imaging system high-throughput seed phenotyping phenotyping software seed heat stress 3D convolutional neural network (CNN) support vector machine (SVM) |
| title | HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds |
| title_full | HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds |
| title_fullStr | HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds |
| title_full_unstemmed | HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds |
| title_short | HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds |
| title_sort | hyperseed an end to end method to process hyperspectral images of seeds |
| topic | hyperspectral imaging system high-throughput seed phenotyping phenotyping software seed heat stress 3D convolutional neural network (CNN) support vector machine (SVM) |
| url | https://www.mdpi.com/1424-8220/21/24/8184 |
| work_keys_str_mv | AT tiangao hyperseedanendtoendmethodtoprocesshyperspectralimagesofseeds AT anilkumarnalinichandran hyperseedanendtoendmethodtoprocesshyperspectralimagesofseeds AT puneetpaul hyperseedanendtoendmethodtoprocesshyperspectralimagesofseeds AT harkamalwalia hyperseedanendtoendmethodtoprocesshyperspectralimagesofseeds AT hongfengyu hyperseedanendtoendmethodtoprocesshyperspectralimagesofseeds |