Support Vector Machine Based Tool for Plant Species Taxonomic Classification
View Abstract View PDF Download PDF

Keywords

Pre-processing, Feature extraction, Hierarchical classification, Multi-class classification, Plant species taxonomy, Support vector machine.

How to Cite

K, M., & MS, V. (2014). Support Vector Machine Based Tool for Plant Species Taxonomic Classification. Journal of Asian Scientific Research, 4(4), 159–173. Retrieved from https://archive.aessweb.com/index.php/5003/article/view/3619

Abstract

Plant species are living things and are generally categorized in terms of Domain, Kingdom, Phylum, Class, Order, Family, Genus and name of Species in a hierarchical fashion. This paper formulates the taxonomic leaf categorization problem as the hierarchical classification task and provides a suitable solution using a supervised learning technique namely support vector machine. Features are extracted from scanned images of plant leaves and trained using SVM. Only class, order, family of plants and species are considered for hierarchical classification in this research work. The trained models corresponding to class - Magnoliopsida, orders - Brassicales, Rosales, families - Cariaceae, Brassicacea, Rosaceae, Rhamnaceae have been used to develop a three level hierarchical classification model for hierarchical classification of plant species and the results are analyzed. A flat multiclass classifier has been built for species which is at last level of hierarchy and the results are analyzed. A user interactive taxonomic tool has developed for displaying taxonomic ranks of species.

View Abstract View PDF Download PDF

Downloads

Download data is not yet available.