论文信息 - Generalized Cooccurrence Matrix to Classify IRS-1D Images using Neural Network

Generalized Cooccurrence Matrix to Classify IRS-1D Images using Neural Network

This paper presents multispectral texture analysis for classification based on a generalized cooccurrence matrix. Statistical and texture features have been obtained from the first order probability distribution and generalized cooccurrence matrix. The features along with the gray value of the selected pixels are fed into the neural network. Frist, Self Organizing Map (SOM) that is an unsupervised network, has been used for segmentation of IRS-1D images. Then a generalized cooccurrence matrix and first order probability distribution have been extracted from each kind of segments. Texture features have been obtained from generalized cooccurrence matrix. The matrices describe relevant “texture” properties of classes. Next, feature vectors are generated from the extracted features. Then the image is classified by Multilayer Perceptron (MLP) network which has been trained separately using the selected pixels. The method used in this paper has been tested on the IRS-1D satellite image of Iran. The Experimental result is compared to the Maximum Likelihood Classification (MLC) result and it has been shown the MLP method is more accurate than MLC method and also is more sensitive to training sites.

J. Amini | E. Hosseini

[1] JANDER M OREIRA,et al. Neural-based color image segmentation and classification using self-organizing maps , 1996 .

[2] Hujun Yin,et al. On the Distribution and Convergence of Feature Space in Self-Organizing Maps , 1995, Neural Computation.

[3] Keith Godfrey,et al. Applying neural networks to colour image data compression , 1992, TENCON'92 - Technology Enabling Tomorrow.

[4] Richard C. Dubes,et al. Performance evaluation for four classes of textural features , 1992, Pattern Recognit..

[5] Teuvo Kohonen,et al. Self-Organization and Associative Memory , 1988 .

[6] T. Kanade,et al. Color information for region segmentation , 1980 .

[7] Marijke F. Augusteijn,et al. Performance evaluation of texture measures for ground cover identification in satellite images by means of a neural network classifier , 1995, IEEE Trans. Geosci. Remote. Sens..

[8] Ronald R. Coifman,et al. Entropy-based algorithms for best basis selection , 1992, IEEE Trans. Inf. Theory.

[9] Martin A. Riedmiller,et al. A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.