Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network
The feasibility of using hyperspectral imaging with convolutional neural network (CNN) to identify rice seed varieties was studied. Hyperspectral images of 4 rice seed varieties at two different spectral ranges (380–1030 nm and 874–1734 nm) were acquired. The spectral data at the ranges of 441–948 n...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2076-3417/8/2/212 |
| _version_ | 1818280414094032896 |
|---|---|
| author | Zhengjun Qiu Jian Chen Yiying Zhao Susu Zhu Yong He Chu Zhang |
| author_facet | Zhengjun Qiu Jian Chen Yiying Zhao Susu Zhu Yong He Chu Zhang |
| author_sort | Zhengjun Qiu |
| collection | DOAJ |
| description | The feasibility of using hyperspectral imaging with convolutional neural network (CNN) to identify rice seed varieties was studied. Hyperspectral images of 4 rice seed varieties at two different spectral ranges (380–1030 nm and 874–1734 nm) were acquired. The spectral data at the ranges of 441–948 nm (Spectral range 1) and 975–1646 nm (Spectral range 2) were extracted. K nearest neighbors (KNN), support vector machine (SVM) and CNN models were built using different number of training samples (100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1500, 2000, 2500 and 3000). KNN, SVM and CNN models in the Spectral range 2 performed slightly better than those in the Spectral range 1. The model performances improved with the increase in the number of training samples. The improvements were not significant when the number of training samples was large. CNN model performed better than the corresponding KNN and SVM models in most cases, which indicated the effectiveness of using CNN to analyze spectral data. The results of this study showed that CNN could be adopted in spectral data analysis with promising results. More varieties of rice need to be studied in future research to extend the use of CNNs in spectral data analysis. |
| first_indexed | 2024-12-12T23:48:50Z |
| format | Article |
| id | doaj.art-fdc25fdc9c444a81be2c0822d1aab298 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-12T23:48:50Z |
| publishDate | 2018-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-fdc25fdc9c444a81be2c0822d1aab2982022-12-22T00:06:47ZengMDPI AGApplied Sciences2076-34172018-01-018221210.3390/app8020212app8020212Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural NetworkZhengjun Qiu0Jian Chen1Yiying Zhao2Susu Zhu3Yong He4Chu Zhang5College of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, ChinaThe feasibility of using hyperspectral imaging with convolutional neural network (CNN) to identify rice seed varieties was studied. Hyperspectral images of 4 rice seed varieties at two different spectral ranges (380–1030 nm and 874–1734 nm) were acquired. The spectral data at the ranges of 441–948 nm (Spectral range 1) and 975–1646 nm (Spectral range 2) were extracted. K nearest neighbors (KNN), support vector machine (SVM) and CNN models were built using different number of training samples (100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1500, 2000, 2500 and 3000). KNN, SVM and CNN models in the Spectral range 2 performed slightly better than those in the Spectral range 1. The model performances improved with the increase in the number of training samples. The improvements were not significant when the number of training samples was large. CNN model performed better than the corresponding KNN and SVM models in most cases, which indicated the effectiveness of using CNN to analyze spectral data. The results of this study showed that CNN could be adopted in spectral data analysis with promising results. More varieties of rice need to be studied in future research to extend the use of CNNs in spectral data analysis.http://www.mdpi.com/2076-3417/8/2/212hyperspectral imagingvariety identificationrice seedconvolutional neural network |
| spellingShingle | Zhengjun Qiu Jian Chen Yiying Zhao Susu Zhu Yong He Chu Zhang Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network Applied Sciences hyperspectral imaging variety identification rice seed convolutional neural network |
| title | Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network |
| title_full | Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network |
| title_fullStr | Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network |
| title_full_unstemmed | Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network |
| title_short | Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network |
| title_sort | variety identification of single rice seed using hyperspectral imaging combined with convolutional neural network |
| topic | hyperspectral imaging variety identification rice seed convolutional neural network |
| url | http://www.mdpi.com/2076-3417/8/2/212 |
| work_keys_str_mv | AT zhengjunqiu varietyidentificationofsinglericeseedusinghyperspectralimagingcombinedwithconvolutionalneuralnetwork AT jianchen varietyidentificationofsinglericeseedusinghyperspectralimagingcombinedwithconvolutionalneuralnetwork AT yiyingzhao varietyidentificationofsinglericeseedusinghyperspectralimagingcombinedwithconvolutionalneuralnetwork AT susuzhu varietyidentificationofsinglericeseedusinghyperspectralimagingcombinedwithconvolutionalneuralnetwork AT yonghe varietyidentificationofsinglericeseedusinghyperspectralimagingcombinedwithconvolutionalneuralnetwork AT chuzhang varietyidentificationofsinglericeseedusinghyperspectralimagingcombinedwithconvolutionalneuralnetwork |