Application of Multispectral Image Texture to Discriminating Tea Categories Based on DCT and LS-SVM
WU Di1, CHEN Xiao-jing1, 2, HE Yong1*
1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310029, China 2. Department of Physics, Xiamen University, Xiamen 361005, China
Abstract：Based on multispectral digital image texture feature, a new rapid and nondestructive method for discriminating tea categories was put forward. The new method combines the advantages of DCT (discrete cosine transform) and least squares-support vector machine (LS-SVM). In the present study, the images for each sample were captured using a red (R) waveband, near infrared (NIR) waveband and green (G) waveband multispectral digital imager. The three wavebands of image can be combined into one image, which contains more information than images captured by ordinary digital cameras, and the NIR image can catch more information than visible spectrum. Three images for one sample can be obtained simultaneously. Eighty filters were designed based on DCT. One hundred twenty images (twenty for each category) were used for calibration set and one hundred twenty mages (twenty for each category) were used as the prediction. Finally, tea category was classified by LS-SVM. The classification rate using Sd of NIR image was only 73.33%, while it reached 100% using 8 filtered images. The overall results show that the technique combining DCT and SVM can be efficiently utilized for texture recognition of multispectral image, and it also is an effective and simple discrimination way for the tea categories. The whole process is simple and easy to operate, and can be transferred to the industrial world for on-line application.
[1] Valera P, Pablos F, Gonalez A G.. Talanta, 1996, 43: 415. [2] Zuo Y G, Chen H, Deng Y W. Talanta, 2002, 57: 307. [3] Togari N, Kobayashi A, Aishima T. Food. Res. Int., 1995, 28: 495. [4] Horie H, Mukai T, Kohata K. J. Chromatogr., 1997, 785: 332. [5] SHAO Yong-ni, HE Yong(邵咏妮, 何 勇). J. Infrared Millim. Waves(红外与毫米波学报), 2006, 25(6): 478. [6] He Yong, Li Xiaoli, Deng Xunfei. J. Food. Eng., 2007, 79(4): 1238. [7] Manik V, Andrew Z. International Journal of Computer Vision, 2005，62(1-2): 61. [8] Sengur A, Turkoglu I, Ince M C. Expert. Sys. Appl., 2007, 32(2): 527. [9] He Yong, Pan Jiazhi, Zhang Yun. Progress in Biomedical Optics and Imaging-Proceedings of SPIE, 2006, 6047 I: 60471R. [10] CEN Hai-yan, BAO Yi-dan, HE Yong(岑海燕，鲍一丹，何 勇). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(3): 503. [11] SHAO Yong-ni, HE Yong, PAN Jia-zhi, et al(邵咏妮, 何 勇, 潘家志, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(9): 1739. [12] WANG Yan-yan, HE Yong, SHAO Yong-ni, et al(王艳艳，何 勇, 邵咏妮, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(4): 702. [13] YAN Yan-lu, ZHAO Long-lian, HAN Dong-hai, et al(严衍禄, 赵龙莲, 韩东海, 等). NIR Spectral Analysis Foundation and Application(近红外光谱分析基础与应用). Beijing: China Light Industry Press(北京:中国轻工业出版社), 2005. 101. [14] LI Yi, RUAN Qiu-qi(李 毅, 阮秋琦). Journal of Communication(通信学报), 2005, 26(1): 114. [15] Robert E K, David J G, Grant R G. Society of Photo-Optical Instrumentation Engineers, 2000, 39(3): 704. [16] ZHANG Xiang, TIAN Jin-wen, XIAO Xiao-ling, et al(张 翔，田金文，肖晓玲, 等). Signal Processing(信号处理), 2004, 20(2): 208. [17] Suykens J, Vandewalle J. Neural Processing Letters, 1999, 9(3): 293. [18] Lu C, Gestel T Van, Suykens J A K, et al. Artif. Intell. Med., 2003, 28: 281. [19] Pelckmans K, Suykens J A K, Van Gestel, et al. J. LS-SVMlab Toolbox User’s Guide (version 1.5), 2003, http://www.esat.kuleuven.ac.be/sista/lssvmlab/tutorial.
