This Article 
 Bibliographic References 
 Add to: 
Computerized Flow Field Analysis: Oriented Texture Fields
July 1992 (vol. 14 no. 7)
pp. 693-709

An approach to the solution of signal-to-symbol transformation in the domain of flow fields, such as oriented texture fields and velocity vector fields, is discussed. The authors use the geometric theory of differential equations to derive a symbol set based on the visual appearance of phase portraits which are a geometric representation of the solution curves of a system of differential equations. They also provide the computational framework to start with a given flow field and derive its symbolic representation. Specifically, they segment the given texture, derive its symbolic representation, and perform a quantitative reconstruction of the salient features of the original texture based on the symbolic descriptors. Results of applying this technique to several real texture images are presented. This technique is useful in describing complex flow visualization pictures, defects in lumber processing, defects in semiconductor wafer inspection, and optical flow fields.

[1] A. Hanson and E. Riseman, Eds.,Computer Vision Systems. New York: Academic, 1978.
[2] A. R. Rao and R. Jain, "Knowledge representation and control in computer vision systems,"IEEE Expert, pp. 64-79, Spring 1988.
[3] P. J. Besl and R. C. Jain, "Segmentation through variable-order surface fitting,"IEEE Trans. Patt. Anal. Machine Intell., vol. 10, pp. 167-192, Mar. 1988.
[4] P. J. Besl and R. C. Jain, "Three-dimensional object recognition,"ACM Comput. Surveys, vol. 17, no. 1, pp. 75-145, Mar. 1985.
[5] W. Merzkirch,Flow Visualization. New York: Academic, 1974.
[6] K. Imaichi and K. Ohmi, "Quantitative flow analysis aided by image processing of flow visualization photographs," inProc. Third Int. Symp. Flow Visualization, 1983, pp. 365-369.
[7] R. M. Haralick, "Statistical and structural approaches to texture,"Proc. IEEE, vol. 67, pp. 786-804, May 1979.
[8] H. Tamura, S. Mori, and T. Yamawaki, "Textural features corresponding to visual perception,"IEEE Trans. Syst. Man Cybern., vol. SMC-8, pp. 460-473, June 1978.
[9] H. Knutsson and G. H. Granlund, "Texture analysis using two-dimensional quadrature filters," inProc. IEEE Wkshp. Comp. Arch. Patt. Anal. Image Database Mgmt., Oct. 1983.
[10] A. C. Bovik, T. S. Huang, and D. C. Munson, "The effect of median filtering on edge estimation and detection,"IEEE Trans. Patt. Anal. Machine Intell., vol. 9, pp. 181-194, Mar. 1987.
[11] R. Conners, C. W. McMillin, K. Lin, and R. E. Vasquez-Espinosa, "Identifying and locating surface defects in wood: Part of an automated lumber processing system,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-5, pp. 573-582, Nov. 1983.
[12] V. Voort,Applied Metallography. New York: Van Nostrand Reinhold, 1986.
[13] P. A. Godinez, "Inspection of surface flaws and textures,"Sensors, pp. 27-32, June 1987.
[14] A. R. Rao and R. Jain, "A programmable inspection system," inVISION- 87 Conf.(Detroit), June 1987, pp. 12-21 to 12-41.
[15] R. Jain, A. R. Rao, A. Kayaalp, and C. Cole, "Machine vision for semiconductor wafer inspection," inMachine Vision for Inspection and Measurement(H. Freeman, Ed.). New York: Academic, 1989.
[16] A. R. Rao and R. Jain, "A visual language for interactions with computer vision systems," inVision 88, 1988.
[17] K. Noto, H. Ishida, and R. Matsumoto, "A breakdown of the karman vortex street due to the natural convection," inProc. Third Int. Symp. Flow Visualization, 1983, pp. 120-124.
[18] T. S. Huang, "Modeling, analysis and visualization of nonrigid object motion," inInt. Conf. Patt. Recognition, June 1990.
[19] N. Gopal, T. Emmoth, and A. C. Bovik, "Channel interactions in visible pattern analysis," inProc. IEEE Int. Conf. Acoustics Speech Signal Processing, 1989, pp. 1643-1646.
[20] A. R. Rao and B. G. Schunck, "Computing oriented texture fields,"CVGIP: Graphical Models Image Processing, vol. 53, pp. 157-185, Mar. 1991.
[21] S. Lefschetz,Differential Equations: Geometric Theory. New York: Interscience, 1963.
[22] D. K. Arrowsmith and C. M. Place,Ordinary Differential Equations: A Qualitative Approach with Applications. New York: Chapman and Hall, 1982.
[23] M. W. Hirsch and S. Smale,Differential Equations, Dynamical Systems, and Linear Algebra. New York: Academic, 1974.
[24] V. I. Arnold,Ordinary Differential Equations. Cambridge, MA: MIT Press, 1973.
[25] A. R. Rao,A Taxonomy for Texture Description and Identification. New York: Springer Verlag, 1990.
[26] W. J. A. Dahm and K. A. Buch, "High resolution measurement three dimensional (2563) spatio-temporal measurements of the conserved scalar field in turbulent shear-flows," Tech. Rep. GRI-5087-260-1443- 4, Dept. of Aerospace Eng., Univ. of Michigan, Ann Arbor, 1987; presented at the Seventh Symp. Turbulent Shear Flows, Stanford, CA, Aug. 1989.
[27] A. R. Rao and R. Jain, "A classification scheme for visual defects arising in semiconductor wafer inspection,"J. Crystal Growth, vol. 103, pp. 398-406, 1990.
[28] H. Wechsler, "Texture analysis: A survey,"Signal Processing, vol. 2, pp. 271-282, 1980.
[29] M. Kass and A. Witkin, "Analyzing oriented patterns,"Comp. Vision Graphics Image Processing, vol. 37, pp. 362-385, 1987.
[30] E. S. Meieran, P. A. Flinee, and J. R. Carruthers, "Analysis technology for VLSI fabrication,"Proc. IEEE, vol. 75, pp. 908-955, July 1987.
[31] K. Prazdny, "On the information in optical flows,"Comput. Vision Graphics Image Processing, vol. 22, pp. 239-259, 1983.
[32] K. ichi Kanatani, "Structure and motion from optical flow under perspective projection,"Comput. Vision Graphics Image Processing, vol. 38, pp. 122-146, May 1987.
[33] D. J. Heeger, "Optical flow using spatiotemporal filters,"Int. J. Comput. Vision, vol. 1, pp. 279-302, 1988.
[34] J. J. Koenderink and A. J. van Doorn, "Invariant properties of the motion parallax field due to the movement of rigid bodies related to an observer,"Optica Acta, vol. 22, pp. 773-791, 1975.
[35] A. Verri and T. Poggio, "Motion field and optical flow: qualitative properties,"IEEE Trans. Patt. Anal. Machine Intell., vol. 11, pp. 490-498, 1989.
[36] J. Helman and L. Hesselink, "Representation and display of vector field topology in fluid flow data sets,"Comput., pp. 27-36, Aug. 1989.
[37] K. M. Kam Yip, "KAM: Automatic planning and interpretation of numerical experiments using geometric methods," Ph.D thesis, Mass, Inst. Tecnol., Cambridge, AI Lab., 1989.
[38] A. C. Bovik, M. Clark, and W. S. Geisler, "Multichannel texture analysis using localized spatial filters,"IEEE Trans. Patt. Anal. Machine Intell., vol. 12, pp. 55-73, Jan. 1990.
[39] R. Jain, T. Sripradisvarakul, and N. O'Brien, "Symbolic surface descriptors for 3-dimensional object recognition," inProc. SPIE, Jan. 1987.
[40] F. M. Vilnrotter, R. Nevatia, and K. E. Price, "Structural analysis of natural textures,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, pp. 76-89, Jan. 1986.
[41] L. G. C. Hamey, "Computer perception of repetitive textures," Ph.D. thesis, Comput. Sci. Dept., Carnegie Mellon Univ., Pittsburgh, 1988.
[42] I. Iwasaki and H. Tanaka, "On the flow visualization and turbulent measurement on the ripple models," inProc. Third Int. Symp. Flow Visualization, 1983, pp. 681-685.
[43] K. Imaichi and K. Ohmi, "Numerical processing of flow visualization pictures--Measurement of two-dimensional vortex flow,"J. Fluid Mechanics, vol. 129, pp. 283-311, 1983.
[44] "Fractographic features revealed by light microscopy," inMetals Handbook, Vol. 9: Fractography and Atlas of Fractographs(8th ed.). Metals Park, OH: Amer. Soc. Metals.
[45] W. S. MacKenzie,Atlas of Igneous Rocks and Their Textures. New York: Wiley, 1982.
[46] H. Core, W. Cote, and A. Day,Wood Structure and Identification. Syracuse NY: Syracuse University Press, 1979.
[47] A. Panshin, C. D. Zeeuw, and H. Brown,Textbook of Wood Technology. New York: McGraw Hill, 1964.
[48] W. Erteld, H. Mette, and W. Achterberg,Defects in Wood. London: Leonard Hill, 1964.
[49] X. Qinghan and B. Zhaoqi, "An approach to fingerprint identification by using the attributes of feature lines of fingerprints," inEighth Int. Conf. Patt. Recognition, Oct. 1986, pp. 663-5.
[50] I. Huntley and R. M. Johnson,Linear and Nonlinear Differential Equations. New York: Halsted Press, 1979.
[51] A. A. Andronov, E. A. Leontovich, I. I. Gordon, and A. G. Maier,Qualitative Theory of Second-Order Dynamic Systems. New York: Wiley, 1966.
[52] J. Palis, Jr. and W. de Melo,Geometric Theory of Dynamical Systems. New York: Springer-Verlag, 1982.
[53] B. S. Garbow, K. E. Hillstrom, and J. J. More, "Documentation for minpack subroutine hybrd1," Argonne Nat. Lab., Mar. 1980.
[54] J. J. More, "The levenberg-marquardt algorithm, implementation and theory," inLecture Notes in Mathematics 630(G. A. Watson, ed.). New York: Springer-Verlag, 1977.
[55] T. Sallam and A. Mitsunaga, "Visualization and computational studies on the formation and stability of karman vortex streets," inProc. Third Int. Symp. Flow Visualization, 1983, pp. 125-129.
[56] A. K. Jain and R. C. Dubes,Algorithms for Clustering Data. Englewood Cliffs, NJ: Prentice-Hall, 1988.
[57] M. Van Dyke,An Album of Fluid Motion. New York: Parabolic, 1982.
[58] P. J. Besl, "Surfaces in early range image understanding," Ph.D. thesis, EECS Dept., Univ. of Michigan, Ann Arbor, May 1986.
[59] J. Leymarie,Qui etait, Van Gogh?.Geneva: Editions d'Art Albert Skira, 1968 (in French).

Index Terms:
computer vision; computerised pattern recognition; flow field analysis; oriented texture fields; signal-to-symbol transformation; velocity vector fields; geometric theory; differential equations; symbol set; phase portraits; symbolic representation; symbolic descriptors; flow visualization pictures; semiconductor wafer inspection; optical flow fields; computerised pattern recognition; computerised picture processing; differential equations; optical information processing
A.R. Rao, R.C. Jain, "Computerized Flow Field Analysis: Oriented Texture Fields," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 7, pp. 693-709, July 1992, doi:10.1109/34.142908
Usage of this product signifies your acceptance of the Terms of Use.