Fusion of texture features and SBS method for classification of tobacco leaves for automatic harvesting

Abstract

In this paper we propose a new model to classify tobacco leaves for automatic harvesting using feature level fusion. The CIELAB color space model is used to segment leaves from their background. Texture features are extracted from segmented leaves using Haar wavelets and gray level local texture pattern (GLTP) separately. These extracted features are fused using the concatenation rule. Discriminative texture features are then selected using the sequential backward selection (SBS) method. The k-NN classifier is designed to classify tobacco leaves into three classes viz., unripe, ripe and over-ripe. In order to corroborate the efficacy of the proposed model, we have conducted an experimentation on our own dataset consisting of 1,300 images of tobacco leaves captured in sunny and cloudy lighting conditions in a real tobacco field. © 2013 Springer.