Title: Base and apex angles and margin types-based identification and classification from medicinal plants' leaves images
Authors: Suvarna S. Nandyal; Basavaraj S. Anami; A. Govardhan
Addresses: CSE Department, P.D.A. College of Engineering, Gulbarga-585103, Karnataka, India ' K.L.E. Institute of technology, Hubli-580030, Karnataka, India ' JNT University, Kukatpally, Hyderabad, AndraPradesh-500072, India
Abstract: In this paper, we have proposed a method for medicinal plants identification and classification from their leaves images based on base angle, apex angle and margin type. In Ayurveda, medicines are extracted from leaves, roots and stems. Many a times, the plants are recognised by their leaves. Therefore, we have considered leaves images in this work. Adoptive Otsu threshold method is used for segmentation of leafy part from the background. The database includes altogether 900 leaves images representing 18 shapes with different base and apex angles and margins. The leaf images are classified based on features such as widest part of leaf and its location, stem angle, base angle and margin. The two angles and margin features are extracted using trigonometric and chain code approaches respectively. The proposed approach is robust, position, scale and rotation invariant and works for even tender leaves. The average recognition and classification accuracy of 98% is obtained. The work assists novice users of Ayurvedic practitioners.
Keywords: base angles; apex angles; plant identification; plant classification; medicinal plants; plant leaves; leaf segmentation; widest part; leaf margin; Otsu threshold; leaf images; Ayurveda; stem angle.
DOI: 10.1504/IJCVR.2013.056040
International Journal of Computational Vision and Robotics, 2013 Vol.3 No.3, pp.197 - 224
Received: 15 Aug 2012
Accepted: 29 Jan 2013
Published online: 18 Jul 2014 *