Plant Species Recognition Based on Radial Basis Probabilistic Neural Networks Ensemble Classifier

In this paper, a novel and efficient method for plant species identification based on radial basis probabilistic neural networks ensemble classifier (RBPNNE) was proposed. The RBPNNE consists of several different independent neural networks trained by different feature domains of the original images. The final classification results represent a combined response of the individual networks. A plant leaf image database build by ourselves is exploited to test our approach. The experimental results show that the RBPNNC achieves higher recognition accuracy and better classification efficiency than single feature domain.