A graph and PNN-based approach to image classification
Jin Tang, Chunyan Zhang, Bin Luo · 2005
In this paper, a new image classification method is developed. This approach applies graph decomposition and probabilistic neural networks (PNN) to the task of supervised image classification. We use relational graphs to represent image. These graphs are constructed from the feature points of images. Spectra of these graphs are obtained as feature vectors for classification. PNN is adopted to classify image according to the feature vectors. Experimental results show that this method can achieve best result of images classification.