Prediction method of single wheat grain protein content based on hyperspectral image

Wu Jingzhu; Liu Qian; Chen Yan; Liu Cuiling

doi:10.3788/IRLA201645.S123002

The characteristics of wheat protein content has high heritability, so fine-quality breeding can be achieved by selecting the high-protein wheat seed. Combined with chemometric methods' hyperspectral imaging technique was used to build the average model to achieve fast prediction of single wheat seed protein content. In the experiment, 47 unit wheat seed samples' hyperspectral images were collected by GaiaChem-NIR system, and the average spectra was obtained by image process methods. Then, synergy interval partial least squares was applied to select the characteristic spectral regions to optimize the prediction model of wheat seed protein content. The optimal models' determination coefficient is 0.94, the root mean square error of prediction is 0.28%, and the residual predictive deviation(RPD) is 3.30. Finally, the average model was applied to predict the protein content of each pixes of single wheat seed, and calculated the average as the single wheat grain protein content. The experimental results showed that different wheat grain's protein content value predicted by the optimal model existed difference. Ueanwhile, the prediction values varied around the average protein content of its sample, which reflected that the average model is accurate and feasible to predict single wheat grain's protein content. Therefore, the studied method provides a new way to select the high-protein wheat seed in the process of breeding, which can promote the development of wheat fine-quality breeding.

Prediction method of single wheat grain protein content based on hyperspectral image

1. Beijing Key Laboratory of Big Data Technology for Food Safety,School of Computer and Information Engineering,Beijing Technology and Business University,Beijing 100048,China

Received Date: 2016-01-15

Rev Recd Date: 2016-02-25

Publish Date: 2016-05-25

Key words:

Abstract: The characteristics of wheat protein content has high heritability, so fine-quality breeding can be achieved by selecting the high-protein wheat seed. Combined with chemometric methods' hyperspectral imaging technique was used to build the average model to achieve fast prediction of single wheat seed protein content. In the experiment, 47 unit wheat seed samples' hyperspectral images were collected by GaiaChem-NIR system, and the average spectra was obtained by image process methods. Then, synergy interval partial least squares was applied to select the characteristic spectral regions to optimize the prediction model of wheat seed protein content. The optimal models' determination coefficient is 0.94, the root mean square error of prediction is 0.28%, and the residual predictive deviation(RPD) is 3.30. Finally, the average model was applied to predict the protein content of each pixes of single wheat seed, and calculated the average as the single wheat grain protein content. The experimental results showed that different wheat grain's protein content value predicted by the optimal model existed difference. Ueanwhile, the prediction values varied around the average protein content of its sample, which reflected that the average model is accurate and feasible to predict single wheat grain's protein content. Therefore, the studied method provides a new way to select the high-protein wheat seed in the process of breeding, which can promote the development of wheat fine-quality breeding.

HTML

Reference (10)

[1]	Qi Linjuan, Hu Xuexu, Zhou Guiying, et al. Analysis of wheat protein quality in the main province of China in 2004-2011[J]. Scientia Agricultura Sinica, 2012, 45(20):4242-4251. (in Chinese)
[2]	Li Shiping, Wang Suibao, Yang Yujing, et al. Research on wheat protein content genetic law and quality improvement[J]. Chinese Agricultural Science Bulletin, 2005, 21(2):126-128. (in Chinese)
[3]	Feng Hui. Analysis of different wheat grain's protein and starch content variance and the sowing time effect of the quality traits[D]. Zhengzhou:Henan Agricultural University, 2009. (in Chinese)
[4]	Zhang Baohua, Li Jiangbo, Fan Shuxiang, et al. Principle and application of hyperspectral image technology in fruit and vegetable quality and safety nondestructive testing[J]. Spectroscopy and Spectral Analysis, 2014, 34(10):2743-2751. (in Chinese)
[5]	Li Ziyang, Qian Yonggang, Shen Qingfeng, et al. Leaf area index retrieval from remotely sensed hyperspectral data[J]. Infrared and Laser Engineering, 2014, 43(3):944-949. (in Chinese)
[6]	Sun Mei, Chen Xinghai, Zhang Heng, et al. Nondestructive inspect of apple quality with hyperspectral imaging[J]. Infrared and Laser Engineering, 2014, 43(4):1272-1277.(in Chinese)
[7]	Li Dan, He Jianguo, Liu Guishan, et al. Non-destructive detection of moisture content in gherkin using hyperspectral imaging[J]. Infrared and Laser Engineering, 2014, 43(7):2393-2397. (in Chinese)
[8]	GB/T 5511-2008. The kjeldahl method for determination of nitrogen content and crude protein content of grains and legumes[S]. ISO20483, IDT,2006. (in Chinese)
[9]	Rafael C G, Richard E W, Steven L E. Digital Image Processing Using Matlab[M]. Beijing:Publishing House of Electronics Industry, 2005.
[10]	Chen Quansheng, Jiang Pei, Zhao Jiewen. Measurement of total flavone content in snow lotus(Saussurea involucrate)using near infrared spectroscopy combined with interval PLS and genetic algorithm[J]. Spectrochimica Acta Part A:Molecular and Biomolecular Spectroscopy, 2010, 76(1):50-55. (in Chinese)

Prediction method of single wheat grain protein content based on hyperspectral image

doi: 10.3788/IRLA201645.S123002

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views