AUTOMATED CLASSIFICATION OF HAIR CARE PLANTS USING GEOMETRICAL AND TEXTURAL FEATURES FROM LEAF IMAGES: A PATTERN RECOGNITION BASED APPROACH

Abstract

Automated classification plays a vital role in content based image retrieval systemsin addition to many more. Inter-class similarity and intra-class dissimilarity is the main challengeposed by leaf classification. This research work proposed a plant classification system using texturaland geometrical features from leaf images. Six classification models, among which three wereensemble methods, were considered to evaluate the accuracy of proposed technique. Train and teststrategy was adopted to evaluate the performance of different classifiers. Experimental results showedthat the proposed technique outperformed the state of the art. Moreover, it was observed that texturalfeatures outperformed geometrical features. The best accuracy achieved with textural features was100%, whereas it was 98.8% when geometrical features were used. SVM, IBk and Random Treeremained the best classifiers in leaf identification using both types of features. Hence, textural andgeometrical features could be effectively used for plant classification