This Article 
 Bibliographic References 
 Add to: 
Learning Texture Discrimination Masks
February 1996 (vol. 18 no. 2)
pp. 195-205

Abstract—A neural network texture classification method is proposed in this paper. The approach is introduced as a generalization of the multichannel filtering method. Instead of using a general filter bank, a neural network is trained to find a minimal set of specific filters, so that both the feature extraction and classification tasks are performed by the same unified network. We compute the error rates for different network parameters, and show the convergence speed of training and node pruning algorithms. The proposed method is demonstrated in several texture classification experiments. It is successfully applied in the tasks of locating barcodes in the images and segmenting a printed page into text, graphics, and background. Compared with the traditional multichannel filtering method, the neural network approach allows one to perform the same texture classification or segmentation task more efficiently. Extensions of the method, as well as its limitations, are discussed in the paper.

[1] K.K. Benke and D.R. Skinner, "Segmentation of visually similar textures by convolution filtering," The Australian Computer J., vol. 19, no. 3, pp. 134-139, 1987.
[2] D.W. Pagliero,“Distance transforms,” Computer Vision, Graphics, and Image Processing: Graphical models and Image Processing, vol. 54, pp. 56-74, 1992.
[3] T. Chang and C.-C. Jay Kuo, "Texture analysis and classification with tree-structured wavelet transform," USC-SIPI Report #198, Feb. 1992.
[4] J.G. Daugman, "Two-dimensional spectral analysis of cortical receptive field profiles," Vision Research, vol. 20, pp. 847-856, 1980.
[5] J.G. Daugman, "Uncertainty relation for resolution in space, spatial-frequency, and orientation optimized by two-dimensional visual cortical filters," J. Optical Soc. Amer., vol. 2, no. 7, pp. 1,160-1,169, 1985.
[6] D.F. Dunn, W.E. Higgins, and J. Wakeley, "Determining Gabor filter parameters for texture segmentation," Proc. SPIE Intelligent Robots and Computer Vision XI, vol. 1,826, pp. 51-63, 1992.
[7] F. Farrokhnia, "Multi-Channel Filtering Techniques for Texture Segmentation and Surface Quality Inspection," PhD thesis, Michigan State Univ., 1990.
[8] O.D. Faugeras, "Texture analysis and classification using a human visual model," Proc. Third Int'l Conf. Pattern Recognition, pp. 549-552,Tokyo, 1978.
[9] D. Gabor, "Theory of communication," J. IEE(London), vol. 93, pp. 429-457, 1946.
[10] R.M. Haralick, "Statistical and structural approaches to texture," Proc. IEEE, vol. 67, no. 5, pp. 786-804, May 1979.
[11] A.K. Jain and S. Bhattacharjee, “Text Segmentation Using Gabor Filters for Automatic Document Processing,” Machine Vision and Applications, vol. 5, pp. 169-184, 1992.
[12] A.K. Jain and Y. Chen, "Barcode localization using texture analysis," Proc. Second Int'l Conf. Document Analysis and Recognition, pp. 41-44,Tsukuba City, Japan, Oct. 1993.
[13] A.K. Jain and R.C. Dubes, Algorithms for Clustering Data. Englewood Cliffs, N.J.: Prentice Hall, 1988.
[14] A.K. Jain and F. Farrokhnia, “Unsupervised Texture Segmentation Using Gabor Filters,” Pattern Recognition, vol. 24, no. 12, pp. 1167-1186, 1991.
[15] A.K. Jain and K. Karu, "Learning texture discrimination masks," Proc. 1994 IEEE Int'l Conf. Neural Networks, pp. 4,374-4,379,Orlando, June 1994.
[16] A.K. Jain and K. Karu, "Automatic filter design for texture discrimination," Proc. 12th Int'l Conf. Pattern Recognition, vol. 1, pp. 454-458,Jerusalem, Oct. 1994.
[17] A.K. Jain and J. Mao, "Artificial neural network for nonlinear projection of multivariate data," Proc. Int'l Joint Conf. Neural Networks, vol. III, pp. 335-340,Baltimore, June 1992.
[18] A.K. Jain and Y. Zhong, "Page layout segmentation based on texture analysis," under review.
[19] B. Julesz, E.N. Gilbert, L.A. Shepp, and H.L. Frisch, "Inability of humans to discriminate between textures that agree in second-order statistics—revisited," Perception, vol 2, pp. 391-405, 1973.
[20] K.I. Laws, "Textured image segmentation," PhD thesis, Univ. of Southern California, 1980.
[21] Y. Le Cun, L.D. Jackel, B. Boser, J.S. Denker, H.P. Graf, I. Guyon, D. Henderson, R.E. Howard, and W. Hubbard, "Handwritten digit recognition: Applications of neural network chips and automatic learning," IEEE Comm. Magazine. Nov. 1989.
[22] J. Mao and A.K. Jain, “Texture Classification and Segmentation Using Multiresolution Simultaneous Autoregressive Models,” Pattern Recognition, vol. 25, no. 2, 1992.
[23] J. Mao and A.K. Jain, "Discriminant analysis neural networks," Proc. Joint Conf. Neural Networks,San Francisco, Apr. 1993.
[24] J. Mao, K. Mohiuddin, and A.K. Jain, "Parsimonious Network Design and Feature Selection Through Node Pruning," Proc. 12th ICPR,Jerusalem, pp. 622-624, 1994.
[25] E. Oja, "Neural networks, principal components, and subspaces," Int'l J. Neural Systems, no. 1, pp.61-68, 1989.
[26] E. Oja and J. Lampinen, "Unsupervised learning for feature extraction," Computational Intelligence Imitating Life, J.M. Zurada, R.J. Marks II, C.J. Robinson, eds., IEEE Inc., pp. 13-22, 1994.
[27] D.A. Pomerleau, Neural Network Perception for Mobile Robot Guidance. Kluwer Academic Publisher, 1993.
[28] T. Randen and J.H. Husøy, "Multichannel filtering for image texture segmentation," to appear in Optical Engineering.
[29] W. Niblack, R. Barber, W. Equitz, M. Flickner, E. Glasman, T. Petkovic, P. Yanker, C. Faloutsos, and G. Taubin, "The QBIC project: Querying images by content using color, texture, and shape," Research report, IBM Almaden Research Center, San Jose, Calif., 1993.
[30] R. Reed, "Pruning algorithms—A survey," IEEE Trans. Neural Networks, vol. 4, no. 5, pp. 740-747, Sept. 1993.
[31] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, "Learning Internal Representations by Error Propagation," Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1: Foundations, D.E. Rumelhart and J.L. McClelland et al., eds., chapter 8, pp. 318-362.Cambridge, Mass.: MIT Press, 1986.
[32] M. Tuceryan and A.K. Jain, “Texture Analysis,” Handbook Pattern Recognition and Computer Vision, C.H. Chen, L.F. Pau, and P.S.P. Wang, eds., Singapore: World Scientific, pp. 235-276, 1993.
[33] L. Van Gool, P. Dewaele, and A. Oosterlinck, "Texture analysis anno 1983," Computer Vision, Graphics, and Image Processing, vol. 29, pp. 336-357, 1985.

Index Terms:
Texture, segmentation, learning, neural networks, feature extraction.
Anil K. Jain, Kalle Karu, "Learning Texture Discrimination Masks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 2, pp. 195-205, Feb. 1996, doi:10.1109/34.481543
Usage of this product signifies your acceptance of the Terms of Use.