Classificação de texturas usando redes neurais artificiais e o modelo de Spot Noise

• Antonio Cesar Germano Martins UNESP
• Alexandre da Silva Simões UNESP
• Gustavo Imbrizi Prado UNESP

Resumo

Este trabalho apresenta um processo de classificação de texturas aleatórias utilizando uma rede neural artificial para a análise de um conjunto de parâmetros característicos do espectro de potência. O modelo de Spot Noise é utilizado como guia para a interpretação de texturas aleatórias, fundamentação para a definição dos parâmetros e análise dos resultados obtidos. São também discutidos detalhes sobre a definição da arquitetura da rede neural artificial empregada bem como os testes realizados.

Referências

Basset, O., Buquet, B., Abouelkaram, S., Delachartre, P. e Culioli, J. (2000) “Application of texture image analysis for the classification of bovine meat”, Food Chemestry, 69, p. 437-445.

Chen, C. C. e Chen, C. C. (1999) “Filtering methods for Texture Discrimination”, Pattern Recognition Letters”, v. 20, p. 783-790.

Christodoulou, C. I., Pattichis, C. S., Pantziaris, M. e Nicolaides, A. (2003) “Texture-based classification of atherosclerotic carotid plaques”, IEEE Transactions on Medical Imaging, v. 22, no. 7, p. 902-912.

Haykin, S. (1999). “Neural Networks: a comprehensive foundation” 2 ed., Upper Saddle River: Prentice-Hall.

Jain, A. K. e Karu, K. (1996a) “Learning Texture Discrimination Masks”, IEEE Transactions on Pattern Analysis and Machine Intelligence, v. 18, no. 2.

Jain, A. K., Mao, J. e Mohiuddin, K.M. (1996b) “Artificial Neural Networks: A Tutorial”, Computer, v. 9, no. 3, p. 31-44.

Jernigan, M. E. e DíAstous, F. (1984) “Entropy-Based Texture Analysis in the Spatial Frequency Domain”, IEEE Transactions on Pattern Recognition and Machine Intelligence, v. PAMI-6, no. 2.

Kachouie, N. N. e Alirezaie, J. (2003) “Texture Segmentation using Gabor Filter and Multi-Layer Perceptron”, Proceedings of the IEE International Conference on Systems, Man and Cybernetics, v.3, p. 2897-2902.

Madablushi, A. E. e Metaxas, D. N. (2003) “Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions”, IEEE Transactions on Medical Imaging, v. 22, n. 2, p.155-169.

Martins, A .C .G, Rangayyan, R.M e Ruschioni, R.A. (2001) “Audification and sonification of texture images”, Journal of Electronic Imaging, 10(3), p. 690-705.

Ojala, T., Pietikäinen, M. e Nisula, J. (1996) “Determining composition of grain mixtures by texture classification based on feature distribution”, International Journal of Pattern Recognition and Artificial Intelligence, 10 (1), p. 73-81.

Paget, R. D. e Longstaff, D. (1996) “Terrain mapping of radar satellite images”, Electronic Imaging, 6(2), p. 6-7.

Quevedo, R., Carlos, L, Aguilera, J. M. e Cadoche, L. (2002) “Description of food surfaces and microstructural changes using fractal image texture analysis”, Journal of Food Engineering, 53, p. 361-371.

Rao, A. R. (1990) “A Taxonomy for texture description and identification”, Nova York: Springer-Verlag.

Weszka, J. S., Dyer, C. R. e Rosenfeld, A. (1976) “A Comparative Study of Texture Measures for Terrain Classification”, IEEE Transactions on Systems, Man, and Cybernetics, v. SMC-6, no. 4, p. 269-285.

Wijk, J. J. (1991) “Spot Noise”, Computer Graphics, 25(4), p. 309-318.