Abstract
A texture image classification system based on the semi-cover vector (SCV) and the bi-directional associative orthonormalized memory (BAOM) is described. The SCV is an statistic extraction method of texture features derived from the fractal geometry. It is invariant under geometric transformations. The BAOM is a neural network with a hidden layer of neurons that increases the learning capacity and reduces the noisy effect. This classifier works in real time and produces about 95.13% of correct classification rate.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
N.R. Pal and S.K. Pal, A review on image segmentation techniques, Pattern Recognition, Vol. 26, No.9, pp. 1277–1294, 1993.
R.M. Haralick, Statistical and strucctural approaches to texture, Procc. IEEE, Vol. 67, pp. 786–804, 1979
C. Neubauer, Segmentation of defects in textile fabric, Procc. IEEE, pp. 688–691, 1992.
W.Huang and R.Lippmann, Comparison between neural net and conventional classifier, IEEE First Int. Conf. Neural Networks, Vol. IV, pp. 485–492, 1987.
R.O. Duda and P.E. Hart, Pattern recognition and scene analysis, New York, Wiley, 1973.
B.B. Mandelbrot, Fractal geometry, Freeman, New York 1993.
J.M.G. Chamizo and A.C.Llorente, Orthonormalized associative memories, Prccc. IJCNN, Baltimore, vol. 1. pp. 476–481, 1992
J.M.G. Chamizo and F.I. Picó, Bidirectional associative orthonormalized memory, Procc. AEPIA, Madrid, 1993.
F.I. Picó and J.M.G.Chamizo, Genralized Bidimensional Associative memory with a hidden orthonormalized layer, Procc. ICANN, 1994.
C-M. Wu and Y-C. Chen, Multi-threshold dimension vector for texture anlysis and its application to liver tissue classification, Pattern Recognition, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Asensi Muñoz, D., Almagro León, A., Ibarra Picó, F. (1995). Texture classification on real time using semi-cover vector and an orthogonal neural network. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_272
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_272
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive