Butterfly Classification by HSI and RGB Color Models Using Neural Networks
Keywords:
Perceptron, back-propagation, neural networks, butterfly, color analysis
Abstract
This study aims the classification of Butterfly species through the implementation of Neural Networks and Image Processing. A total of 9 species of Morpho genre which has blue as a characteristic color are processed. For Butterfly segmentation we used image processing tools such as: Binarization, edge processing and mathematical morphology. For data processing RGB values are obtained for every image which are converted to HSI color model to identify blue pixels and obtain the data to the proposed Neural Networks: Back-Propagation and Perceptron. For analysis and verification of results confusion matrix are built and analyzed with the results of neural networks with the lowest error levels. We obtain error levels close to 1% in classification of some Butterfly species.
How to Cite
[1]
J. E. Grajales-Múnera and A. Restrepo-Martinez, “Butterfly Classification by HSI and RGB Color Models Using Neural Networks”, TecnoL., pp. 669–679, Nov. 2013.
Downloads
Download data is not yet available.
Published
2013-11-19
Issue
Section
Computer science