Perception Based On Its Incline And Pier Using Centroid Delineation Pitch Of Leaf
Journal Title: International Journal of Research in Computer and Communication Technology - Year 2015, Vol 4, Issue 3
Abstract
With the aim of elaborating a mobile application, accessible to anyone and with educational purposes, wepresent a method for tree species identification that relies on dedicated algorithms and explicit botanyinspireddescriptors. Focusing on the analysis of leaves, we developed a working process to help recognizespecies, starting from a picture of a leaf in a complex natural background. A two-step active contoursegmentation algorithm based on a polygonal leaf model processes the image to retrieve the contour ofthe leaf. This paper suggests normalization of the tip and base of leaf asboth of them incline to one direction which is able toinfluencedata extraction process. The extraction method we used isCentroid Contour Gradient (CCG) which calculates the gradientbetween pairs of boundary points corresponding to interval angle.CCG had butperformed its competitor which is CentroidContours Distance (CCD), as it successfully captures thecurvature of the tip and base of leaf. The accuracy in classifyingthe tip of leaf using CCG is 99.47%, but CCD is only 80.30%.For accuracy of leaf base classification, CCG (98%) alsooutperforms CCD (88%). The average accuracy for recognizingthe 5 classes of plant is 96.6% for CCG and 74.4% for CCD. Inthis research, we utilized the Feed-forward Backpropagation asour classifier.Features we use afterwards are high-level geometrical descriptors that make a semantic interpretationpossible, and prove to achieve better performance than more generic and statistical shapedescriptors alone. We present the results, both in terms of segmentation and classification, consideringa database of 50 European broad-leaved tree species, and an implementation of the system is availablein the iPhone application Folia.
Authors and Affiliations
Sandeep Thangirala, Jhansi Rani S
Keywords
Related Articles
- EP ID EP28154
- DOI -
- Views 263
- Downloads 1
Data Security in Cloud Computing using RSA Algorithm
Cloud Computing is an emerging paradigm which has become today’s hottest research area due to its ability to reduce the costs associated with computing. In today’s era, it is most interesting and enticing technology whi...
Time Series Data Mining Tool
A time series is a sequence of data points, measured typically at successive points in time spaced at uniform time intervals. Time series analysis comprises methods for analyzing time series data in order to extract...
Image Depth Approximation using Bezier-Bernstein polynomial for 3D cameras
passive depth estimation techniques with improved precision can replace active methods in 3D cameras. In this paper, we introduce accurate depth estimation from image focus using cubic degree Bezier-Bernstein polynomi...
Study on Business Process Reengineering(BPR) and its importance in ERP Implementation
In the new era of automation in the industrial growth the ERP plays vital role. Most of the industries struggle to steady their business as much as automatic at the level of functioning environment. The ERP is the one...
An Approach to Identify Node Clones in Wireless Sensor Networks
Sensor nodes that are deployed in hostile environments are susceptible to capture and compromise. An adversary may gain private information from these sensors, clone and logically deploy them in the network to launch...