1. Institute of Vegetables and Flowers,Chinese Academy of Agricultural Sciences,Beijing 100081,China 2. National Laboratory of Color Science and Engineering,Beijing Institute of Technology,Beijing 100081,China
Abstract:Hyperspectral imaging(400-720 nm) and discriminate analysis were investigated for the detection of normal and diseased cucumber leaf samples with powdery mildew(Sphaerotheca fuliginea), angular leaf spot(Pseudomopnas syringae), downy mildew(Pseudoperonospora cubensis), and brown spot(Corynespora cassiicola). A hyperspectral imaging system was established to acquire and pre-process leaf images, as well as to extract leaf spectral properties. Owing to the complexity of the original spectral data, stepwise discriminate and canonical discriminate were executed to reduce the numerous spectral information, in order to decrease the amount of calculation and improve the accuracy. By the stepwise discriminate we selected 12 optimal wavelengths from the original 55 wavelengths, and after the canonical discriminate, the 55 wavelengths were reduced to 2 canonical variables. Then the discriminate models were developed to classify the leaf samples. The result shows that the stepwise discriminate model achieved classification accuracies of 100% and 94% for the training and testing sets, respectively. For the canonical model, the classification accuracies for the training and testing sets were both 100%. These results indicated that it is feasible to identify and classify cucumber diseases using hyperspectral imaging technology and discriminate analysis. The preliminary study, which was done in a closed room with restrictions to avoid interference of the field environment, showed that there is a potential to establish an online field application in cucumber disease detection based on visible spectroscopy.
[1] LI Bao-ju(李宝聚). China Vegetables(中国蔬菜),2006,(1):1. [2] WANG Hui-zhe,LI Shu-ju,HUO Zhen-rong,et al(王惠哲,李淑菊,霍振荣,等). Acta Agriculturae Boreali-Sinica(华北农学报),2006,21(1):105. [3] ZHANG Dong-ying,HONG Jin,TANG Wei-ping,et al(张冬英,洪 津,汤伟平,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2008,28(10):2455. [4] LIU Xing-ku,LI Zhao-hua(刘兴库,李兆华). Journal of Northeast Forestry University(东北林业大学学报),1993,21(2):106. [5] MA Ling,CUI De-qi,WANG Rui,et al(马 玲,崔德琪,王 瑞,等). Optical Technique(光学技术),2006,32(8):573. [6] QIAN Le-xiang,PAN Xue-qin,ZHAO Qian(钱乐祥,泮学芹,赵 芊). Remote Sensing For Land & Resources(国土资源遥感),2004,2:1. [7] Bravo C,Moshou D,West J,et al. Biosystems Engineering,2003,84(2):137. [8] Cui D, Zhang Q,Li M Z,et al. Sensing and Instrumentation for Food Quality and Safety,2009,3:49. [9] Kim M S,Chen Y R,Meh P M. Transactions of the ASAE,2001,44 (3) :721. [10] TAN Hai-zhen,LI Shao-kun,WANG Ke-ru,et al(谭海珍,李少昆,王克如,等). Acta Agronomica Sinica (作物学报),2008,34(10):1812. [11] GAO Hui-xuan(高惠璇). Practical Statistical Methods and SAS System(实用统计方法与SAS系统). Beijing:Peking University Press(北京:北京大学出版社),2001. 147.