Classification of Camellia (Theaceae) Species Using Leaf Architecture Variations and Pattern Recognition Techniques

Leaf characters have been successfully utilized to classify Camellia (Theaceae) species; however, leaf characters combined with supervised pattern recognition techniques have not been previously explored. We present results of using leaf morphological and venation characters of 93 species from five sections of genus Camellia to assess the effectiveness of several supervised pattern recognition techniques for classifications and compare their accuracy. Clustering approach, Learning Vector Quantization neural network (LVQ-ANN), Dynamic Architecture for Artificial Neural Networks (DAN2), and C-support vector machines (SVM) are used to discriminate 93 species from five sections of genus Camellia (11 in sect. Furfuracea, 16 in sect. Paracamellia, 12 in sect. Tuberculata, 34 in sect. Camellia, and 20 in sect. Theopsis). DAN2 and SVM show excellent classification results for genus Camellia with DAN2's accuracy of 97.92% and 91.11% for training and testing data sets respectively. The RBF-SVM results of 97.92% and 97.78% for training and testing offer the best classification accuracy. A hierarchical dendrogram based on leaf architecture data has confirmed the morphological classification of the five sections as previously proposed. The overall results suggest that leaf architecture-based data analysis using supervised pattern recognition techniques, especially DAN2 and SVM discrimination methods, is excellent for identification of Camellia species.

[1]  Ludovic Duponchel,et al.  Comparison of supervised pattern recognition methods with McNemar’s statistical test: Application to qualitative analysis of sugar beet by near-infrared spectroscopy , 2003 .

[2]  Felipe Espinosa,et al.  Comparison of neural classifiers for vehicles gear estimation , 2011, Appl. Soft Comput..

[3]  Hu Hui,et al.  Leaf morphology and anatomy of Camellia section Camellia (Theaceae) , 2009 .

[4]  Quansheng Chen,et al.  Study on discrimination of Roast green tea (Camellia sinensis L.) according to geographical origin by FT-NIR spectroscopy and supervised pattern recognition. , 2009, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[5]  Giuseppe Messina,et al.  Discrimination and identification of morphotypes of Banksia integrifolia (Proteaceae) by an Artificial Neural Network (ANN), based on morphological and fractal parameters of leaves and flowers. , 2009 .

[6]  Jingfeng Huang,et al.  Application of neural networks to discriminate fungal infection levels in rice panicles using hyperspectral reflectance and principal components analysis , 2010 .

[7]  Quansheng Chen,et al.  Feasibility study on identification of green, black and Oolong teas using near-infrared reflectance spectroscopy based on support vector machine (SVM). , 2007, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[8]  Manoochehr Ghiassi,et al.  Measuring effectiveness of a dynamic artificial neural network algorithm for classification problems , 2010, Expert Syst. Appl..

[9]  Jiewen Zhao,et al.  Identification of green tea's (Camellia sinensis (L.)) quality level according to measurement of main catechins and caffeine contents by HPLC and support vector classification pattern recognition. , 2008, Journal of pharmaceutical and biomedical analysis.

[10]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[11]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[12]  Cheng Haozhong,et al.  Fault diagnosis of power transformer based on multi-layer SVM classifier , 2005 .

[13]  Tsvi Kuflik,et al.  Automating Personal Categorization Using Artificial Neural Networks , 2001, User Modeling.

[14]  V. Mosbrugger,et al.  Evolution and Function of Leaf Venation Architecture: A Review , 2001 .

[15]  Hong Zheng,et al.  Using neural networks to estimate the losses of ascorbic acid, total phenols, flavonoid, and antioxidant activity in asparagus during thermal treatments. , 2010, Journal of agricultural and food chemistry.

[16]  . M.SikanderHayatKhiyal,et al.  Classification of Textual Documents Using Learning Vector Quantization , 2007 .

[17]  A. Premoli.  Leaf architecture of South American Nothofagus (Nothofagaceae) using traditional and new methods in morphometrics , 1996 .

[18]  David Zimbra,et al.  A dynamic artificial neural network model for forecasting time series events , 2005 .

[19]  Camellia japonica L. genotypes identified by an artificial neural network based on phyllometric and fractal parameters , 2007, Plant Systematics and Evolution.

[20]  Wen-Ju Zhang,et al.  Molecular taxonomy of Camellia (Theaceae) inferred from nrITS sequences. , 2009, American journal of botany.

[21]  O. Bruno,et al.  Leaf shape analysis using the multiscale Minkowski fractal dimension, a new morphometric method: a study with Passiflora (Passifloraceae) , 2005 .

[22]  L. Hickey.  CLASSIFICATION OF THE ARCHITECTURE OF DICOTYLEDONOUS LEAVES , 1973 .

[23]  C. Cleal.  A new species of "Neuropteris" from the Middle Westphalian of Palencia , 1981 .

[24]  Yong Chen,et al.  Neural network prediction of ascorbic acid degradation in green asparagus during thermal treatments , 2011, Expert Syst. Appl..

[25]  R. Melville.  THE TERMINOLOGY OF LEAF ARCHITECTURE , 1976 .

[26]  Vladimir Naumovich Vapni.  The Nature of Statistical Learning Theory , 1995 .

[27]  Ping Ye,et al.  Classification and Recognition of Plant Leaf Based on Neural Networks , 2011 .

[28]  Dominique Baillargeat,et al.  An accurate wavelet neural-network-based model for electromagnetic optimization of microwave circuits , 1999 .

[29]  C. G. Cheng,et al.  Comparative leaf anatomy, FTIR discrimination and biogeographical analysis of Camellia section Tuberculata (Theaceae) with a discussion of its taxonomic treatments , 2008, Plant Systematics and Evolution.

[30]  Changjiang Zhang,et al.  A particle swarm optimization-aided fuzzy cloud classifier applied for plant numerical taxonomy based on attribute similarity , 2009, Expert systems with applications.

[31]  Hong Zheng,et al.  Use of kinetic, Weibull and PLSR models to predict the retention of ascorbic acid, total phenols and antioxidant activity during storage of pasteurized pineapple juice , 2011 .

[32]  Zhang Xin-hua,et al.  Leaf Architecture of Subtribe Micheliinae (Magnoliaceae) from China and Its Taxonomic Significance , 2007 .

[33]  Javad Alirezaie,et al.  Neural network based segmentation of magnetic resonance images of the brain , 1995, 1995 IEEE Nuclear Science Symposium and Medical Imaging Conference Record.

[34]  Asoke K. Nandi,et al.  FAULT DETECTION USING SUPPORT VECTOR MACHINES AND ARTIFICIAL NEURAL NETWORKS, AUGMENTED BY GENETIC ALGORITHMS , 2002 .

[35]  S. Cevallos-Ferriz,et al.  Bauhcis moranii gen. et sp. nov. (Cercideae, Caesalpinieae), an Oligocene plant from Tepexi de Rodrı́guez, Puebla, Mex., with leaf architecture similar to Bauhinia and Cercis , 2002 .

[36]  Manoochehr Ghiassi,et al.  A dynamic artificial neural network model for forecasting nonlinear processes , 2009, Comput. Ind. Eng..

[37]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[38]  E. Köhler.  Blattnervatur‐Muster der Buxaceae DUMORTIER und Simmondsiaceae VAN TIEGHEM Mit 7 Abbildungen , 1993 .

[39]  Jiewen Zhao,et al.  Detection of Bruise on Pear by Hyperspectral Imaging Sensor with Different Classification Algorithms , 2010 .

[40]  Giles M. Foody,et al.  The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM , 2006 .

[41]  Q. Peng,et al.  Leaf anatomy of Camellia sect. Oleifera and sect. Paracamellia (Theaceae) with reference to their taxonomic significance , 2007 .

[42]  Wisnu Jatmiko,et al.  Fuzzy-neuro LVQ and its comparison with fuzzy algorithm LVQ in artificial odor discrimination system. , 2002, ISA transactions.

[43]  K. Héberger,et al.  Supervised pattern recognition in food analysis. , 2007, Journal of chromatography. A.

[44]  Liang Chen,et al.  Genetic improvement and breeding of tea plant (Camellia sinensis) in China: from individual selection to hybridization and molecular breeding , 2007, Euphytica.

[45]  Ya Hu,et al.  Bruise detection on red bayberry (Myrica rubra Sieb. & Zucc.) using fractal analysis and support vector machine , 2011 .

[46]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[47]  J. Chen,et al.  Identification of SVM-based classification model, synthesis and evaluation of prenylated flavonoids as vasorelaxant agents. , 2008, Bioorganic & medicinal chemistry.

[48]  Tamer Ölmez,et al.  Classification of heart sounds using an artificial neural network , 2003, Pattern Recognit. Lett..

[49]  Jian Huang,et al.  Precise plant classification within genus level based on simulated annealing aided cloud classifier , 2011, Expert Syst. Appl..

[50]  D. T. Prasad,et al.  Implementation of Epileptic EEG using Recurrent Neural Network , 2010 .

[51]  Hong Zheng,et al.  Automatic sorting of Chinese jujube (Zizyphus jujuba Mill. cv. ‘hongxing’) using chlorophyll fluorescence and support vector machine , 2010 .

[52]  J. Sealy.  A revision of the genus camellia , 1958 .

[53]  Hongfei Lu,et al.  Relevance of Fourier transform infrared spectroscopy and leaf anatomy for species classification in Camellia (Theaceae) , 2008 .

[54]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[55]  Robert W. Hess,et al.  Anatomy of the Dicotyledons. , 1950 .

[56]  Manoochehr Ghiassi,et al.  A dynamic architecture for artificial neural networks , 2005, Neurocomputing.

[57]  Changsheng Xie,et al.  Identification and pattern recognition analysis of Chinese liquors by doped nano ZnO gas sensor array , 2005 .

[58]  Conor Meade,et al.  Multivariate analysis of leaf shape patterns in Asian species of the Uvaria group (Annonaceae) , 2003 .

[59]  M. Möller,et al.  Taxonomic treatments of Camellia (Theaceae) species with secretory structures based on integrated leaf characters , 2010, Plant Systematics and Evolution.

[60]  Sergio Mugnai,et al.  Artificial neural networks as a tool for plant identification: a case study on Vietnamese tea accessions , 2009, Euphytica.