Abstract:The seed maturity, which is one of the important factors that affect seed vigor, is an important quality index. During seed sorting, separating mature seeds from immature seeds can improve the vigor of seed lot and keep vigor consistency. Hyperspectral imaging that covered the range of 400~1 000 nm was used to find out the sensitive bands reflecting corn seed maturity, and corresponding images were employed to classify the immature corn seeds. Principal component analysis (PCA) algorithm was adopted to analyze the hyperspectral image. PC2 of PCA had the greatest difference between immature and mature areas on the seeds, therefore, the weighted coefficients of PC2 was selected to extract sensitive wavebands (501 nm). Regions of interest (ROI) from mature and immature area of 70 immature kernels was selected for mean spectra calculation. Partial least square regression (PLSR) algorithm was employed to analyze the spectra of ROI and extract wavelength related to maturity (518 nm). Band ratio algorithm and Kruskal-Wallis test were used to select the best band ratio that had the biggest difference between mature and immature areas (640 nm/525 nm). 864 kernels of corn seed were analyzed by gray images of the selected wavelengths as well as band ratio images. Results showed that the light color regions of the seed crown were misidentified as immature region when the images of selected single band wavelengths were used, while the band ratio image of 640 nm/525 nm could be identified correctly. The immature seeds can be separated from the mature seeds according to the area ratio of segmented immature region to the whole kernel. The correct recognition rate was 93.9%. Using the grey images of selected band ratio can differentiate immature corn seeds from mature seeds effectively, which provide a theoretical reference for the development of seed sorting device in further work.
Key words:Corn seed;Precision planting;Hyperspectral imaging;Maturity;Band ratio;Kruskal-Wallis test
杨小玲,由昭红,成 芳* . 高光谱成像技术检测玉米种子成熟度 [J]. 光谱学与光谱分析, 2016, 36(12): 4028-4033.
YANG Xiao-ling, YOU Zhao-hong, CHENG Fang* . Study on Identification of Immature Corn Seed Using Hyperspectral Imaging. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(12): 4028-4033.
[1] ZHAO Xia, WANG Xiao-xing, HUANG Rui-dong, et al(赵 霞,王小星,黄瑞冬,等). Journal of Maize Sciences(玉米科学), 2012, 20(4): 95. [2] SUN Qun, WANG Jian-hua, SUN Bao-qi(孙 群,王建华,孙宝启). Scientia Agricultura Sinica, 2007, 40(1): 48. [3] WANG Hong-wei, DONG Jia-li(王宏伟,董家利). Seed Science & Technology(种子科技),2007, 3: 42. [4] Tekrony D, Egli D. Basic and Applied Aspects of Seed Biology, 1997,30: 369. [5] Knittle K, Burris J. Crop Science, 1976, 16(6): 851. [6] Hunter J, TeKrony D, Miles D, et al. Crop Science, 1991, 31(5): 1309. [7] TeKrony D, Hunter J. Crop Science, 1995, 35: 857. [8] SHI Hai-chun, KE Yong-pei, FU Ti-hua,et al(石海春,柯永培,傅体华,等). Journal of Sichuan Agricultural University(四川农业大学学报), 2006, 24(3): 269. [9] WANG Zhong-xiao, DU Cheng-gui, WANG Qing-cheng(王忠孝,杜成贵,王庆成). Shandong Agricultural Sciences(山东农业科学)1986, 4: 36. [10] Santos C, Dalpasquale V, Scapim C et al. Brazilian Archives of Biology and Technology, 2005, 48(2): 161. [11] YANG Jin-zhong, ZHANG Hong-sheng, SONG Xi-yun,et al(杨锦忠,张洪生,宋希云,等). Journal of Maize Sciences(玉米科学), 2011, 19(2): 148. [12] Ma Y, Huang M, Yang B et al. Computers and Electronics in Agriculture, 2014, 106: 102. [13] Fox G, Manley M. Journal of the Science of Food and Agriculture, 2014, 94(2): 174. [14] Kruskal W, Wallis W. Journal of the American Statistical Association,1952, 47(260): 583. [15] SHENG Li-dong(盛立东). Introduction to Pattern Recognition(模式识别导论). Beijing: Beijing University of Posts and Telecommunications Press(北京:北京邮电大学出版社), 2010. 239. [16] Liu D, Sun D, Zeng X. Food and Bioprocess Technology, 2014, 7(2): 307. [17] CAI Jian-rong, WANG Jian-hei, CHEN Quan-sheng,et al(蔡健荣,王建黑,陈全胜,等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2009, 25(1): 127.