Multi-Target Recognition of Internal and External Defects of Potato by Semi-Transmission Hyperspectral Imaging and Manifold Learning Algorithm
HUANG Tao1, LI Xiao-yu1*, JIN Rui1, KU Jing1, XU Sen-miao1, XU Meng-ling1, WU Zhen-zhong1, KONG De-guo1,2
1. College of Engineering, Huazhong Agricultural University, Wuhan 430070, China 2. College of Mechanical and Electronic Engineering, Tarim University, Alaer City 843300, China
Abstract:The present paper put forward a non-destructive detection method which combines semi-transmission hyperspectral imaging technology with manifold learning dimension reduction algorithm and least squares support vector machine (LSSVM) to recognize internal and external defects in potatoes simultaneously. Three hundred fifteen potatoes were bought in farmers market as research object, and semi-transmission hyperspectral image acquisition system was constructed to acquire the hyperspectral images of normal external defects (bud and green rind) and internal defect (hollow heart) potatoes. In order to conform to the actual production, defect part is randomly put right, side and back to the acquisition probe when the hyperspectral images of external defects potatoes are acquired. The average spectrums (390~1 040 nm) were extracted from the region of interests for spectral preprocessing. Then three kinds of manifold learning algorithm were respectively utilized to reduce the dimension of spectrum data, including supervised locally linear embedding (SLLE), locally linear embedding (LLE) and isometric mapping (ISOMAP), the low-dimensional data gotten by manifold learning algorithms is used as model input, Error Correcting Output Code (ECOC) and LSSVM were combined to develop the multi-target classification model. By comparing and analyzing results of the three models, we concluded that SLLE is the optimal manifold learning dimension reduction algorithm, and the SLLE-LSSVM model is determined to get the best recognition rate for recognizing internal and external defects potatoes. For test set data, the single recognition rate of normal, bud, green rind and hollow heart potato reached 96.83%, 86.96%, 86.96% and 95% respectively, and he hybrid recognition rate was 93.02%. The results indicate that combining the semi-transmission hyperspectral imaging technology with SLLE-LSSVM is a feasible qualitative analytical method which can simultaneously recognize the internal and external defects potatoes and also provide technical reference for rapid on-line non-destructive detecting of the internal and external defects potatoes.
Key words:Hyperspectral imaging;Manifold learning;Error correcting output code;Least squares support vector machine;Internal and external defects;Potato
[1] ZHOU Zhu, LI Xiao-yu, TAO Hai-long, et al(周 竹, 李小昱, 陶海龙, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2012, 28(21): 221. [2] WANG Cheng-long, LI Xiao-yu, WU Zhen-zhong, et al(汪成龙, 李小昱, 武振中, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2014, 30(1): 245. [3] GAO Hai-long, LI Xiao-yu, XU Sen-miao, et al(高海龙, 李小昱, 徐森淼, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2013, 29(15): 279. [4] Dacal-Nieto A, Formella A, Carrión P, et al. Computer Analysis of Images and Patterns. Germany: Springer Berlin Heidelberg Press, 2011. 180. [5] DONG Chao, ZHAO Hui-jie(董 超, 赵慧洁). Journal of Beijing University of Aeronautics and Astronautics(北京航空航天大学学报), 2010, 36(8): 957. [6] WEN Jin-huan, TIAN Zheng, LIN Wei, et al(温金环, 田 铮, 林 伟, 等).Journal of Computer Applications(计算机应用), 2011, 31(3): 715. [7] de Ridder D, Kouropteva O, Okun O, et al. Artificial Neural Networks and Neural Information Processing-ICANN/ICONIP 2003. Germany: Springer Berlin Heidelberg Press, 2003. 333. [8] Roweis S T, Saul L K. Science, 2000, 290(5500): 2323. [9] Tenenbaum J B, De Silva V, Langford J C. Science, 2000, 290(5500): 2319. [10] Suykens J A K, Vandewalle J. Neural Processing Letters, 1999, 9(3): 293. [11] Dietterich T G, Bakiri G. Journal of Artificial Intelligence Research, 1995, 3(2): 263.