Abstract：As an effective method for the nondestructive measurement of agricultural products quality, hyperspectral imaging technology has been widely studied in the field of seed classification and identification. Feature extraction and optimal wavelength selection are the two critical issues affecting the application of hyperspectral image in the field of seed identification. This study aimed to select optimal wavelengths from hyperspectral image data using joint skewness algorithm, so that they can be deployed in multispectral imaging-based inspection system for the automatic classification of maize seed. The hyperspectral images covering the wavelength range of 438～1 000 nm were acquired for 960 maize seeds including 10 varieties. After extracting the mean spectrum and entropy from the hyperspectral images, the joint skewness algorithm was used to select optimal wavelengths, and the classification models based on support vector machine were developed using the mean spectrum, entropy, and their combination, respectively. The experimental results indicated that the classification accuracy of the models developed by combination of the mean spectrum and entropy were higher than that of the mean spectrum or entropy for either full wavelengths or optimal wavelengths. The classification model for the combination of the mean spectrum and entropy based on the 10 optimal wavelengths selected by the joint skewness algorithm obtained 96.28% accuracy for test samples, with improvements of 4.30% and 20.38% over that of the mean spectrum and entropy, respectively, which was higher than the classification accuracy of the model that developed in the full wavelength (i.e., 93.47%). Meanwhile, the classification model based on joint skewness algorithm yielded the better classification accuracy than that of uninformative viable elimination algorithm, successive projections algorithm, and competitive adaptive reweighed sampling algorithm. This study made the online application of the hyperspectral image technology available for seed identification.
[1] Yang Yanli, Miao Changyun, Li Xianguo, et al. Optik, 2014, 125: 5803. [2] Cheng Shuxi, Sun Wenwen, Zhang Chu, et al. Spectroscopy and Spectral Analysis, 2014, 34(9): 2519. [3] Alireza P, Hamidreza P, Mohammad A, et al. Computers and Electronics in Agriculture, 2012, 83: 102. [4] Mohammed K, Sun Da-wen, Gamal E, et al. Talanta, 2013, 103: 130. [5] Teena M, Manickavasagan A, Ravikanth L, et al. Journal of Stored Products Research, 2014, 59: 306. [6] Ramón M, Francesco C, Amaury L, et al. Neurocomputing, 2014, 128: 207. [7] Tan Kezhu, Chai Yuhua, Song Weixian, et al. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30: 235. [8] Wang Lu, Liu Dan, Pu Hongbin, et al. Food Analytical Methods, 2015, 8: 515. [9] Hu Menghan, Dong QingLi, Liu BaoLin. Postharvest Biology & Technology, 2016, 115: 122. [10] Adrianode A G, Agustina V S, Héctor C G, et al. Anal. Bioanal. Chem., 2015, 407: 5649. [11] Fan Shuxiang, Zhang Baohua, Li Jiangbo, et al. Biosystems Engineering, 2016, 143: 9. [12] Huang Min, Zhao Weiyan, Wang Qingguo, et al. International Agrophysics, 2015, 29: 39. [13] Huang Min, Ma Yanan, Li Yanhua, et al. Analytical Methods, 2014, 6: 7793. [14] Geng Xiurui, Ji Luyan, Sun Kang. IEEE Geoscience and Remote Sensing Letters, 2014, 11: 1821. [15] Geng Xiurui, Ji Luyan, Zhao Yongchao, et al. IEEE Geosci and Remote Sens. Lett., 2013, 10: 1305. [16] Yang Xiaoling, Hong Hanmei, You Zhaohong, et al. Sensors, 2015, 15: 15578. [17] Zhu Qibing, Feng Zhaoli, Huang Min, et al. Transactions of the Chinese Society of Agricultural Engineering, 2012, 23: 271.
