Title :
Classification of selected medicinal plant leaves using texture analysis
Author :
Sathwik, T. ; Yasaswini, R. ; Venkatesh, R. ; Gopal, Aarthi
Author_Institution :
Chennai Centre, Central Electron. Eng. Res. Inst., Chennai, India
Abstract :
Plants play one of the most important roles in our ecosystem. But the rapid decline in the variety of plants is an issue which demands our immediate attention. The first logical step would be the identification of the different plant species by the botanists. Manual identification can often be time consuming and inaccurate. Plants also play a major role in ayurvedic and modern forms of medicine. There is an urgent need to identify and classify the medicinal plants. For this purpose we need an automated and reliable tool which can easily identify and classify plants using available information. So this paper aims at developing such a method to identify and classify medicinal plants from their leaf images using texture analysis of the images as a basis for classification. The software identifies and returns the closest match of the query image from the database based on its texture features. Next the texture features obtained by texture analysis are tested individually on the test leaves to identify the most efficient among them. A combination of these texture features is used for classification and the success rate is recorded.
Keywords :
biology computing; botany; feature extraction; image classification; image matching; image retrieval; image texture; image texture analysis; leaf image; medicinal plant leaves classification; plant species identification; query image matching; texture feature; Biomedical imaging; Computers; Databases; Entropy; Feature extraction; Reliability; Software; Dissimilarity; Gray level co-occurrence matrix; Image processing; Leaf classification; Texture analysis; Texture features;
Conference_Titel :
Computing, Communications and Networking Technologies (ICCCNT),2013 Fourth International Conference on
Conference_Location :
Tiruchengode
Print_ISBN :
978-1-4799-3925-1
DOI :
10.1109/ICCCNT.2013.6726793