Leaves Recognition V1.0 PDF Print E-mail
Written by Rizki Noor Hidayat Wijayaź   

LeavesRecognition is a neuronal network based java application/applet to recognize images of leaves accordingly to a previously trained Backpropagation Network.

The intention of this application is to give the user the ability to administrate a hierarchical list of leaf images, where he can performe some sort of edge detection to identify the individual tokens of every image. This tokens will then be the basis of the neuronal network calculations to make it possible to recognize a unknown leaf image and specify the species it belongs to.

The main purpose of this application/documentation should be to show that the outer frame of a leaf and a Backpropagation Network is enough to give a reasonable statement about the species it belongs to

The development started in July 2001 based on a study project of Jens Langner at the University of Applied Sciences Dresden (HTW) and was completed in late August.

To realize the above mentioned purpose and to make it possible to use this application on nearly every operating system, the choosen programming language for the implementation is Java.

Beside the fact of writing a java based application to realize this purpose, one addtional feature is that it could also be used as a java applet to directly give the user the ability to start it via a java enabled internet browser.

[download: 3,07 MB]