Tea Category Identification using Computer Vision and Generalized Eigenvalue Proximal SVM

• Autorzy: Wang S. , Phillips P. , Liu A. , Du S.

Identyfikatory

DOI

10.3233/FI-2017-1495

• Języki publikacji: EN

Abstrakty

EN

(Objective) In order to increase classification accuracy of tea-category identification (TCI) system, this paper proposed a novel approach. (Method) The proposed methods first extracted 64 color histogram to obtain color information, and 16 wavelet packet entropy to obtain the texture information. With the aim of reducing the 80 features, principal component analysis was harnessed. The reduced features were used as input to generalized eigenvalue proximal support vector machine (GEPSVM). Winner-takes-all (WTA) was used to handle the multiclass problem. Two kernels were tested, linear kernel and Radial basis function (RBF) kernel. Ten repetitions of 10-fold stratified cross validation technique were used to estimate the out-of-sample errors. We named our method as GEPSVM + RBF + WTA and GEPSVM + WTA. (Result) The results showed that PCA reduced the 80 features to merely five with explaining 99.90% of total variance. The recall rate of GEPSVM + RBF + WTA achieved the highest overall recall rate of 97.9%. (Conclusion) This was higher than the result of GEPSVM + WTA and other five state-of-the-art algorithms: back propagation neural network, RBF support vector machine, genetic neural-network, linear discriminant analysis, and fitness-scaling chaotic artificial bee colony artificial neural network.

Słowa kluczowe

EN

tea category identification; computer vision; color histogram; wavelet packet entropy; winner-takes-all; radial basis function; artificial neural network; pattern recognition; support vector machine

• Wydawca: IOS Press
• Czasopismo: Fundamenta Informaticae
• Rocznik: 2017
• Tom: Vol. 151, nr 1/4
• Strony: 325--339
• Opis fizyczny: Bibliogr. 24 poz., rys., tab., wykr.

Twórcy

autor

Wang S.

• School of Electronic Science and Engineering, Nanjing University, Nanjing, Jiangsu 210046, China

autor

Phillips P.

• Department of Supply Chain Management, W. P. Carey School of Business, Arizona State University, P.O. Box 873406, Tempe, AZ 85287, USA

autor

Liu A.

• College of Communications Engineering, PLA University of Science and Technology, Nanjing, Jiangsu 210007 – China

autor

Du S.

• School of Electronic Science and Engineering, Nanjing University, Nanjing, Jiangsu 210046, China

Bibliografia

• [1] Yang CS, Landau JM. Effects of tea consumption on nutrition and health. Journal of Nutrition. 2000; 130 (110): 2409-2412.
• [2] Sironi E (et al.). Natural Compounds against Neurodegenerative Diseases: Molecular Characterization of the Interaction of Catechins from Green Tea with A beta 1-42, PrP106-126, and Ataxin-3 Oligomers. Chemistry-a European Journal. 2014; 20 (42): 13793-13800. doi: 10.1002/chem.201403188.
• [3] Bohn SK (et al.). Effects of black tea on body composition and metabolic outcomes related to cardiovascular disease risk: a randomized controlled trial. Food & Function. 2014; 5 (7): 1613-1620. doi: 10.1039/c4fo00209a.
• [4] Qi H and Li SX. Dose-response meta-analysis on coffee, tea and caffeine consumption with risk of Parkinson's disease. Geriatrics & Gerontology International. 2014; 14 (2): 430-439. doi: 10.1111/ggi.12123.
• [5] Lim HJ, (et al.). Green tea catechin leads to global improvement among Alzheimer’s disease-related phenotypes in NSE/hAPP-C105 Tg mice. Journal of Nutritional Biochemistry. 2013; 24 (7): 1302-1313. doi: 10.1016/j.jnutbio.2012.10.005.
• [6] Yiannakopoulou EC. Green Tea Catechins: Proposed Mechanisms of Action in Breast Cancer Focusing on the Interplay Between Survival and Apoptosis. Anti-Cancer Agents in Medicinal Chemistry. 2014; 14 (2): 290-295. doi: 10.2174/18715206113136660339.
• [7] Shi WM, (et al.). Tea Classification by Near Infrared Spectroscopy with Projection Discriminant Analysis and Gene Expression Programming. Analytical Letters. 2015; 48 (18): 2833-2842. doi: 10.1080/00032719.2015.1055574.
• [8] Herrador MA and Gonzalez AG. Pattern recognition procedures for differentiation of Green, Black and Oolong teas according to their metal content from inductively coupled plasma atomic emission spectrometry. Talanta. 2001; 53 (6): 1249-1257.
• [9] Chen QS, (et al.). Feasibility study on identification of green, black and Oolong teas using near-infrared reflectance spectroscopy based on support vector machine (SVM). Spectrochimica Acta Part a-Molecular and Biomolecular Spectroscopy. 2007; 66 (3): 568-574. doi: 10.1016/j.saa.2006.03.038.
• [10] Jian W, Xianyin Z, and ShiPing D. Identification and grading of tea using computer vision. Applied Engineering in Agriculture. 2010; 26 (4): 639-645. doi: 10.13031/2013.32051.
• [11] Chen Q, Zhao J, and Cai J. Identification of tea varieties using computer vision. Transactions of the Asabe. 2008; 51 (2): 623-628. doi: 10.13031/2013.24363.
• [12] Borah S, Hines EL, and Bhuyan M. Wavelet transform based image texture analysis for size estimation applied to the sorting of tea granules. Journal of Food Engineering. 2007; 79 (2): 629-639. Available from: http://dx.doi.org/10.1016/j.jfoodeng.2006.02.022.
• [13] Gill GS, Kumar A, and Agarwal R. Monitoring and grading of tea by computer vision - A review. Journal of Food Engineering. 2011; 106 (1): 13-19. doi: 10.1016/j.jfoodeng.2011.04.013.
• [14] Laddi A, (et al.). Classification of tea grains based upon image texture feature analysis under different illumination conditions. Journal of Food Engineering. 2013; 115 (2): 226-231. doi: 10.1016/j.jfoodeng.2012.10.018.
• [15] Zhang Y, (et al.). Fruit classification using computer vision and feedforward neural network. Journal of Food Engineering. 2014; 143 (0): 167-177. doi: 10.1016/j.jfoodeng.2014.07.001.
• [16] Tai YH, Chou LS, and Chiu HL. Gap-Type a-Si TFTs for Front Light Sensing Application. Journal of Display Technology. 2011; 7 (12): 679-683. doi: 10.1109/JDT.2011.2164054.
• [17] de Almeida VE, (et al.). Using color histograms and SPA-LDA to classify bacteria. Analytical and Bioanalytical Chemistry. 2014; 406 (24): 5989-5995. doi: 10.1007/s00216-014-8015-l.
• [18] Li YB, (et al.). Radar emitter signal recognition based on multi-scale wavelet entropy and feature weighting. Journal of Central South University. 2014; 21 (11): 4254-4260. doi: 10.1007/s11771-014-2422-5.
• [19] Moshrefi R, Mahjani MG, and Jafarian M. Application of wavelet entropy in analysis of electrochemical noise for corrosion type identification. Electrochemistry Communications. 2014; 48: 49-51. doi: 10.1016/j.elecom.2014.08.005.
• [20] Yang YH, (et al.). Wavelet kernel entropy component analysis with application to industrial process monitoring. Neurocomputing. 2015; 147: 395-402. doi: 10.1016/j.neucom.2014.06.045.
• [21] Mangasarian OL, and Wild EW. Multisurface proximal support vector machine classification via generalized eigenvalues. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006; 28 (l): 69-74. doi: 10.1109/TPAMI.2006.17.
• [22] Khemchandani R, Karpatne A, and Chandra S. Generalized eigenvalue proximal support vector regressor. Expert Systems with Applications. 2011; 38 (10): 13136-13142. doi: 10.1016/j.eswa.2011.04.121.
• [23] Shao YH, (et al.). Improved Generalized Eigenvalue Proximal Support Vector Machine. IEEE Signal Processing Letters. 2013; 20 (3): 213-216. doi: 10.1109/LSP.2012.2216874.
• [24] Rossatto DR, (et al.). Fractal analysis of leaf-texture properties as a tool for taxonomic and identification purposes: a case study with species from Neotropical Melastomataceae (Miconieae tribe). Plant Systematics & Evolution. 2011; 291 (291): 103-116. doi: 10.1007/s00606-010-0366-2.