Optimal Wavelengths Extraction of Apple Brix and Firmness Based on Hyperspectral Imaging

被引：0
|
作者：
Feng D. [1 ,2 ]
Ji J.-W. [1 ]
Zhang L. [3 ]
Liu S.-J. [1 ]
Tian Y.-W. [1 ]
机构：
[1] College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang
[2] Liaoning Radio and Television, Shenyang
[3] Liaoning Radio and Television Transmission Center, Shenyang
来源：
Tian, You-Wen (youwen_tian10@163.com) | 1600年 / Editorial Office of Chinese Optics卷 / 38期
关键词：
Apple; GA-BP; Hyperspectral imaging; Optimal wavelength; Two times SPA;
D O I：
10.3788/fgxb20173806.0799
中图分类号：
学科分类号：
摘要：
Hyperspectral imaging technology was used to extract the optimal wavelength for apple brix and firmness test. Firstly, the hyperspectral images of apples were acquired from double-sided sampling. The reflection waveforms of the regions of interest (RIOs) with similar brightness were acquired and smoothed by the second derivation and standard normal variate (SD+SNV) method. The brix and firmness values of RIOs were also tested. Then, the characteristic wavelengths of two indicators were extracted by using the successive projections agorithm(SPA). According to the distribution of characteristics wavelengths, two times SPA was proposed. Combined the feature of waveforms and the results of two projections, the optimal wavelengths of different sampling facets were determined. Finally, the genetic algorithm for back propagation(GA-BP) was used to build the prediction model. The best results were obtained from the double-sided sampling wavelengths (543 nm and 674 nm). The correlation coefficient of brix (R) is 0.847 6 and the mean square error (MSE) is 3.32, and for the firmness, R is 0.793 8 and MSE is 9.6. The results show that the brix and firmness can be detected by the same wavelength information. © 2017, Science Press. All right reserved.
引用
收藏
页码：799 / 806
页数：7
相关论文
共 14 条
  • [1] Sun M., Chen X.H., Zhang H., Et al., Nondestructive inspect of apple quality with hyperspectral imaging, Infrared Laser Eng., 43, 4, pp. 1272-1277, (2014)
  • [2] Wu L.G., He J.G., He X.G., Et al., Research progress of hyperspectral imaging technology in non-destructive detection of fruit, Laser Infrared, 43, 9, pp. 990-996, (2013)
  • [3] Gong Y.J., Zhou T., Qu Y.K., Et al., Online analysis on Hanfu apple quality spectral information based on NDT, J. Shenyang Agric. Univ., 45, 6, pp. 708-713, (2014)
  • [4] Wang B.J., Huang M., Zhu Q.B., Et al., UVE-LLE classification of apple mealiness based on hyperspectral scattering image, Acta Photon. Sinica, 40, 8, pp. 1132-1136, (2011)
  • [5] Huang H., Zheng X.L., Luo F.L., Hyperspectral image classification with combination of weighted mean filter and manifold reconstruction preserving embedding, Acta Photon. Sinica, 45, 10, (2016)
  • [6] Guo Z.M., Huang W.Q., Peng Y.K., Et al., Impact of region of interest selection for hyperspectral imaging and modeling of sugar content in apple, Mod. Food Sci. Technol., 30, 8, pp. 59-63, (2014)
  • [7] Guo J.X., Rao X.Q., Cheng G.S., Et al., Prediction of the sugar degree and grading of Xinjiang Fuji apple by hyper-spectral imaging techniques, J. Xinjiang. Agric. Univ., 35, 1, pp. 78-86, (2012)
  • [8] Zhao J.W., Chen Q.S., Saritporn V., Et al., Determination of apple firmness using hyperspectral imaging technique and multivariate calibrations, Trans. CSAE, 25, 11, pp. 226-231, (2009)
  • [9] Wang S., Huang M., Zhu Q.B., Model fusion for prediction of apple firmness using hyperspectral scattering image, Comput. Electron. Agric., 80, pp. 1-7, (2012)
  • [10] Mendoza F., Lu R.F., Ariana D., Et al., Integrated spectral and image analysis of hyperspectral scattering data for prediction of apple fruit firmness and soluble solids content, Postharvest Biol. Technol., 62, 2, pp. 149-160, (2011)
12