Abstract
In the present paper a new method is proposed which involves teaching an Artificial Neural Network with a hierarchical data structure. This method results in a recognition process that significantly reduces the duration of a training process that is generally time consuming. The proposed method uses an invariant Octree data structure to describe the volume of a three dimensional object. The object is thus transformed in such a way that it is independent of rotation, translation and scaling and provides a significant storage capacity compression rate.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
A. Rosenfeld, “ Quadtrees and Pyramids for pattern recognition and image processing”, Proc. 5th Int. Conf. on Pattern Recognition, Miami Beach, 1–4 Dec 1980, 802–811.
G.M. Hunter, “Linear transformation of pictures represented by Quadtree”, Comput. Graphics Image Processing, vol 10, no 3, July 1979, 289–296.
M. Imme, “A new method for edge detection”, IEE 3rd Int. Conf. on Image processing and its applications, Number 307, University of Warwick, U.K., 18–20 July 1989, 656–659.
A. Klinger, “Pattern and search statistics”, Optimised Methods in Statistics, J.S. Ustagi,ed., Academic Press, New York 1971.
H. Samet, “Connected component labelling using quadtrees”, J. ACM., vol 28, no 3, 1981, 487–501.
A. Klinger, M. L. Rhodes, “Organization and access of image data by areas”, IEEE PAMI-1, 1979, 50–60.
G.M. Hunter, K. Steiglitz, “Operations on images using Quadtrees”, IEEE PAMI-1, 1979, 145–153.
H. Samet, “Region representation: Quadtrees from binary arrays”, Comp. Graph. Image Proc., vol 13, 1980, 88–93.
H. Samet, “An algorithm to convert rasters to quadorees”, IRRF. PAMI-3, 1981, 93–95.
H. Samet, “Neighbour finding in Quadtrees”, Proc. PRIP-81, Dallas, Aug. 3–5 1981, 68–74.
C. R. Dyer, A. Rosenfeld, H. Samet, “Region representation: boundary codes from quadtrees”, Comm. Ass. Comput. Mach. 23, 1980, 171–179.
M. Shneier, “Path length distances for Quadtrees”, Inf. Sci. 23, 1981, 45–67.
L. Jones, S.S. Iyengar, “Representation of a region by a forest of quadtrees”, MEF. PRIP-81 Conf., Dallas, 1981, 57–59.
J. R. Woodwark, “The explicit quadtree as a structure for Computer Graphics”, Comput. J., vol 25, no 2, 1982, 235–238.
L Gargantini, “An effective way to represent quadtrees”, Comm. ACM, vol 25, no 12, 1983, 905–910.
M.A. Oliver, N.E. Wiseman, “Operations on quadtree encoded images”, Compt. J., vol 26, no 1, 1983, 83–91.
G. M. Morton, “A computer oriented geodetic data base and a new technique in file sequencing”, IBM Canada, 1966.
M. Tamminen, “Encoding pixel trees”, Comput. Vision Graph. and Image Proc., vol 28, no 1, 1984, 4457.
L Gargantini, “An effective way to store quadtrees”, Comm. Ass. Comput. Mach. 25, 1982, 905–910.
A. Klinger, C.R. Dyer, “Experiments on picture representation using regular decomposition”, Comp. graph. Image Proc., Vol 5, 1976, 68–105.
S. Tanimoto, T. Pavlidis, “A hierarchical data structure for picture processing”, Comput. Graphics and Image Processing, vol 4, 1975, 104–119.
M. Li, W.L Grosky, R. Jain, “Normalised Quadtrees with respect to translations”, Proc. PRIP-81, Dallas, Texas, Aug. 3–51981, 60–62.
C.H. Chien, J.K. Aggarwal, “Volume/Surface Octrees for the representation of three dimensional Objects”, Comp. Graphics Image Proc., Vol 36, 1986, 100–113.
C.H. Chien, J.K. Aggarwal, “Normalised Quadtree Representation”, Comp. Vis. Graphics Image Proc., vol 26, 1984, 331–346.
M.M. Yau, S.N. Srihari, “A hierarchical data structure for multidimensional digital images”, Comm. ACM, vol 26, no7, 1983, 504–515.
S.N. Srihari, “Representations of 3D digital images”, Comput. Surveys 13, 1981, 394–424.
C.L. Jackins, S.L. Tan imoto, “Quadtrees, Octrees, and K-trees: A generalised approach to recursive decomposition of euclidean space”, IEEE PAMI-5, no 5, 1983, 533–539.
L Calborn, L Charkrarartn, Vanderschel, “A hierarchical data structure for representing the spatial decomposition of 3D objects”, IEEE Comp. Graphics Appl. 5, no 4, 1985, 24–31.
D. J. Abel, J. L. Smith, “A data structure and algorithm based on linear key for rectangular retrieval problems”, Comput. Vision Graphics and Image Proc., vol 24, 1983, 1–13.
C.I. Conolly, “Cumulative generation of Octree models from range data”, Proc. Int. Conf. Robotics, Atlanta, March 13–15, 1984, 25–32.
C. H. Chien, J. K. Aggarwal, “Identification of 3D objects from multiple silhouettes using Quadtrees/Octrees”, Comput. Vision Graphics and Image Proc. 36, 1986, 256–273.
J. Veestra, N. Ahuja, “Efficient Octree generation from silhouettes”, Proc. IEEE Comp. Soc. Conf. on Comp. Vision and Pattern Recognition, Miami Beach, June 22–26, 1986, 537–542.
C.H. Chien, J.K. Aggarwal, “Computation of Volume./Surface Octrees from Contours and Silhouettes of Multiple Views”, Proceedings CVPR’86, IFFF. Computer Society, Jun. 1986, 250–255.
A.A.G. Requicha, “Representations for rigid solids: Theory, methods, and systems”, Comp. Surveys, vol 12, no 4, 1980, 437–464.
J. Austin, T.J. Stonham, “An associative memory for use in image recognition and occlusion analysis”, Vision and Image Computing, Vol 5, no 4, Nov. 1987, 251–261.
J. Austin, “ADAM: An Associative neural architecture for invariant pattern classification”, lEE Conference on Artificial Neural Networks, lEE Conf. Publication 313, London 1989, 196–200.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag London Limited
About this paper
Cite this paper
Mertzanis, E.C., Austin, J. (1992). Linear Quadtrees for Neural Network Based Position Invariant Pattern Recognition. In: Taylor, J.G. (eds) Neural Network Applications. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-2003-2_7
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2003-2_7
Publisher Name: Springer, London
Print ISBN: 978-3-540-19772-0
Online ISBN: 978-1-4471-2003-2
eBook Packages: Springer Book Archive