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

Abstract

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.

Classification of Camellia species from 3 sections using leaf anatomical data with back-propagation neural networks and support vector machines

“…In the present paper, for the first time, we employed 2 supervised pattern recognition techniques (BP-ANN and SVM) to achieve high classification accuracy when classifying Camellia species, especially using the RBF-SVM classifier in comparison with the Camellia taxonomic systems of Chang (1998). Compared with other methods, such as the LVQ classifier and DAN2 classifier used by Lu et al (2012), the RBF-SVM classifier in our study produces a more accurate result. The techniques, like methods and accuracies of systems, used in classification of fruits and vegetables are various (Guyer and Yang, 2000;Moshou et al, 2003;, but it is difficult for accuracies to reach the classification results of RBF-SVM used in our study.…”

ASSESSMENT OF TAXONOMIC AFFINITY OF INDONESIAN PUMMELO (<i>CITRUS MAXIMA</i> (BURM.) MERR.) BASED ON MORPHOLOGICAL CHARACTERS

“…Meanwhile, Viscosi and Cardini (2011) noted the importance of leaf morphology in taxonomy and thus developed a protocol to facilitate the use of leaf characters in numerical taxonomy. Moreover, Lu et al (2012) reported that analysis on the leaf architectural types was useful for the identification and classification of Camelia and thus gave more support on the role of leaves morphology in taxonomy.…”

Plant Recognition Using Stereo Leaf Image Using Gray-Level Co-Occurrence Matrix

“…Gray-Level Co-occurrence Matrix (GLCM) is one of the well-known texture analysis methods to estimate the image properties related to second-order statistics (Lu et al, 2012). The matrix is designed to measure the spatial relationship between pixels.…”

“…This The recognition of plants is very important to study the genetic diversity of plant (Singh et al, 2011;Lu et al, 2012), ecological sensitivity, environmental durability, the maintenance of atmospheric composition, nutrient cycle and other ecosystem processes (Du and Wang, 2011). Some researchers developed the recognition of plant to manage food production (Wu et al, 2009), to recognize medicinal plants (Ershad, 2011;Pornpanomchai et al, 2011a), to manage and control the growth of plants (Chuanyu et al, 2011) and to meet the objectives of research in the field of botany.…”