
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
G.J. Salem, T.Y. Young, "A Neural Network Approach to the Labeling of Line Drawings," IEEE Transactions on Computers, vol. 40, no. 12, pp. 14191424, December, 1991.  
BibTex  x  
@article{ 10.1109/12.106227, author = {G.J. Salem and T.Y. Young}, title = {A Neural Network Approach to the Labeling of Line Drawings}, journal ={IEEE Transactions on Computers}, volume = {40}, number = {12}, issn = {00189340}, year = {1991}, pages = {14191424}, doi = {http://doi.ieeecomputersociety.org/10.1109/12.106227}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Computers TI  A Neural Network Approach to the Labeling of Line Drawings IS  12 SN  00189340 SP1419 EP1424 EPD  14191424 A1  G.J. Salem, A1  T.Y. Young, PY  1991 KW  computer vision; neural network approach; labeling of line drawings; modified Hopfield networks; energy function; updating equation; physical model; neurons; Boolean AND operations; trihedral scenes; Boolean functions; computer vision; neural nets. VL  40 JA  IEEE Transactions on Computers ER   
A solution to the labeling of the drawings using a neural network approach is presented. Linelabeling constraints are designed into a modified Hopfield networks. The design of the energy function and the updating equation is described. The energy function includes higher order terms than in the usual quadratic Hopfield model to accommodate the higherorder interactions required by the labeling constraints. The physical model is modified accordingly. An additional layer of neurons is used to synthesize a realizable circuit. The resulting network combines the standard Hopfieldnetwork neurons with neurons performing two and threeway Boolean AND operations. Simulation of network behavior for various trihedral scenes produced successful results.
[1] S. R. Yhann and T. Y. Young, "A multiresolution approach to texture segmentation using neural networks," inProc. Tenth Int. Conf. Pattern Recognition, Atlantic City, NJ, vol. 1, June 1990, pp. 513517.
[2] N. R. Dupaguntla and V. Vemuri, "A neural network architecture for texture segmentation and labeling," inProc. Int. Joint Conf. Neural Networks, Washington, DC, vol. 1, June 1989, pp. 127133.
[3] C. Cortes and J. A. Hertz, "A network system for image segmentation," inProc. Int. Joint Conf. Neural Networks, Washington, DC, June 1989, pp. 121125.
[4] Y. T. Zhou, R. Chellappa, A. Vaid, and B. K. Jenkins, "Image restoration using a neural network,"IEEE Trans. Acoust., Speech, Signal Processing, vol. 36, no. 7, pp. 11411151, 1988.
[5] J. G. Daugman, "Complete discrete 2d Gabor transforms by neural networks tor image analysis and compression,IEEE Trans. Acoust. Speech Signal Proc., vol. 36, no. 7, pp. 11691179, 1988.
[6] A. Carpenter and S. Grossberg, "The art of adaptive pattern recognition by selforganizing neural networks,"IEEE Comput. Mag., vol. 21, pp. 7788, Mar. 1988.
[7] T. A. Jamison and R. J. Schalkoff, "Image labeling: A neural network approach,"Image and Vision Comput., vol. 6, no. 4, pp. 203213, Nov. 1988.
[8] WC. Lin, FY. Liao, CK. Tsao, and T. Lingutla, "A hierarchical multipleview approach to threedimensional object recognition,"IEEE Trans. Neural Networks, vol. 2, pp. 8492, Jan. 1991.
[9] D. H. Ballard and C. M. Brown,Computer Vision. Englewood Cliffs, NJ: PrenticeHall, 1982.
[10] M. B. Clowes, "On seeing things,"Artif. Intell., vol. 2, pp. 79116, 1971.
[11] D. A. Huffman, "Impossible objects as nonsense sentences,"Machine Intell., vol. 6, pp. 295323, 1971.
[12] D. Waltz, "Understanding line drawings of scenes with shadows," inThe Psychology of Computer vision, P. H. Winston, Ed. New York: McGrawHill, 1975.
[13] T. Kanade, "A theory of Origamy world,"Artif Intell., vol. 13, pp. 279311, 1980.
[14] A. K. Mackworth, "Interpreting pictures of polyhedral scenes,"Artif. Intell., vol. 4, pp. 121137, 1973.
[15] K. Sugihara, "Mathematical structure of line drawings of polyhedra toward manmachine communications by means of line drawings,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI4, pp. 458469, 1982.
[16] J. Malik, "Interpreting line drawings of curved objects,"Int. J. Comput. Vision, vol. 1, pp. 73103, 1987.
[17] B. Nudel, "Consistentlabeling problem and their algorithms: Expected complexities and theorybased heuristics,"Artif. Intell., vol. 21, pp. 135178, 1983.
[18] A. Rosenfeld, R. A. Hummel, and S. W. Zucker, "Scene labeling by relaxation operations:IEEE Trans. Syst., Man, Cybern., vol. SMC6, pp. 420433, June 1976.
[19] H. Liu, T. Y. Young, and A. Das, "A multilevel parallel processing approach to scene labeling problems,"IEEE Trans. Pattern Anal. Machine Intell., vol. 10, pp. 586590, July 1988.
[20] J. J. Hopfield, "Neurons with graded response have collective computational properties like those of twostate neurons,"Proc. Nat. Acad. Sci., vol. 81, pp. 30883092, May 1984.
[21] J. J. Hopfield and D. W. Tank, "Neural computation of decisions in optimization problems,"Biol. Cybern., vol. 52, pp. 141152, 1985.
[22] A. Das, "Simulation of parallel processing in discrete scene labeling," Master's thesis, Univ. of Miami, pp. 3743, 1987.