This Article 
 Bibliographic References 
 Add to: 
Unsupervised Segmentation of Textured Images by Edge Detection in Multidimensional Feature
April 1989 (vol. 11 no. 4)
pp. 414-421

An algorithm for unsupervised texture segmentation is developed that is based on detecting changes in textural characteristics of small local regions. Six features derived from two, two-dimensional, noncausal random field models are used to represent texture. These features contain information about gray-level-value variations in the eight principal directions. An algorithm for automatic selection of the size of the observation windows over which textural activity and change are measured has been developed. Effects of changes in individual features are considered simultaneously by constructing a one-dimensional measure of textural change from them. Edges in this measure correspond to the sought-after textural edges. Experiments results with images containing regions of natural texture show that the algorithm performs very well.

[1] P. Brodatz,Texture: A Photographic Album for Artists and Designers. New York: Dover, 1956.
[2] P. C. Chen and T. Pavlidis, "Segmentation by texture using correlation,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, pp. 64-69, Jan. 1983.
[3] J. M. Coggins and A. K. Jain, "A spatial filtering approach to texture analysis,"Pattern Recognition Lett., vol. 3, pp. 195-203, May 1985.
[4] H. Derin and H. Elliott, "Modeling and segmentation of noisy and textured images using Gibbs random fields,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, pp. 39-55, Jan. 1987.
[5] R. C. Gonzalez and P. Wintz,Digital Image Processing. Reading, MA: Addison-Wesley, 1977, pp. 119-127.
[6] L. V. Gool, P. Dewaele, and A. Oosterlinck, "Survey: Texture analysis anno 1983,"Comput. Vision, Graphics, Image Processing. vol. 29, pp. 336-357, 1985.
[7] R. M. Haralick. "Statistical and structural approaches to texture,"Proc. IEEE, vol. 67, pp. 786-804, 1979.
[8] R. L. Kashyap, "Analysis and synthesis of image patterns by spatial interaction models," inProgress in Pattern Recognition, L. N. Kanal and A. Rosenfeld, Ed., vol. 1, New York: North-Holland, 1981, pp. 149-186.
[9] R. Kashyap and R. Chellapa, "Estimation and choice of neighbors in spatial interaction models of images,"IEEE Trans. Inform. Theory, vol. IT-29, pp. 60-72, Jan. 1983.
[10] R. L. Kashyap and A. Khotanzad, "A stochastic model based technique for texture segmentation," inProc. IEEE 7th Int. Conf. Pattern Recognition, Montreal, Canada, July 1984, pp. 1202-1205.
[11] A. Khotanzad and J. Y. Chen, "Unsupervised segmentation of textured images by edge detection in multidimensional features," TR EE 87012, Dep. Elec. Eng., Southern Methodist Univ., Dallas, TX, Aug. 1987.
[12] A. Khotanzad and R. L. Kashyap, "Feature selection for texture recognition using image synthesis,"IEEE Trans. Syst., Man, Cybern., vol. SMC-17, pp. 1087-1095, Nov. 1987.
[13] A. Rosenfeld and A. Kak,Digital Picture Processing, New York: Academic, 1976.
[14] W. B. Thompson, "Textural boundaries analysis,"IEEE Trans. Comput., vol. C-26, pp. 272-276, Mar. 1977.
[15] E. Triendl and T. Henderson, "A model for texture edges," inProc. IEEE 5th Int. Conf. Pattern Recognition, Miami Beach, FL, Dec. 1980, pp. 1100-1102.
[16] M. Unser, "Sum and difference histograms for texture classification,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-8, pp. 118-125, 1986.

Index Terms:
2D noncausal random field models; computerised picture processing; pattern recognition; textured images; edge detection; multidimensional feature; unsupervised texture segmentation; gray-level-value; observation windows; computerised pattern recognition; computerised picture processing
A. Khotanzad, J.Y. Chen, "Unsupervised Segmentation of Textured Images by Edge Detection in Multidimensional Feature," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 4, pp. 414-421, April 1989, doi:10.1109/34.19038
Usage of this product signifies your acceptance of the Terms of Use.