Centroid neural network with Chi square distance measure for texture classification

An unsupervised competitive neural network for efficient classification of image textures is proposed. The proposed neural network architecture, called centroid neural network with Chi square distance measure (CNN-chi²), employs the Chi square measure as its distance measure and utilizes the local binary pattern (LBP) as an effective feature extraction tool for image data. The proposed CNN-chi² is applied to image texture classification problems on the Brodatz texture album database. The results are compared with those of conventional approaches including the HMT (hidden Markov tree), IMM (independence mixture model), and WES (wavelet energy signatures). The evaluated results demonstrate that the proposed CNN-chi² classification algorithm outperforms the conventional algorithms in terms of classification accuracy.