Invariance Signatures: Characterizing Contours by Their Departures from Invariance

In this paper, a new invariant feature of two-dimensional contours is reported: the invariance signature. The invariance signature is a measure of the degree to which a contour is invariant under a variety of transformations, derived from the theory of Lie transformation groups. It is shown that the invariance signature is itself invariant under shift, rotation, and scaling of the contour. Since it is derived from local properties of the contour, it is well-suited to a neural network implementation. It is shown that a model-based neural network (MBNN) can be constructed which computes the invariance signature of a contour and classifies patterns on this basis. Experiments demonstrate that invariance signature networks can be employed successfully for shift-, rotation-, and scale-invariant optical character recognition.

[1]  Lilly Spirkovska,et al.  Higher-order neural networks applied to 2D and 3D object recognition , 1994, Machine Learning.

[2]  Terry Caelli,et al.  Invariant pattern recognition using multiple filter image representations , 1989, Comput. Vis. Graph. Image Process..

[3]  Aaron Heller,et al.  An experimental evaluation of projective invariants , 1992 .

[4]  Isaac Weiss.  Noise-Resistant Invariants of Curves , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Eduardo D. Sontag,et al.  Feedback Stabilization Using Two-Hidden-Layer Nets , 1991, 1991 American Control Conference.

[6]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[7]  Zhi-Qiang Liu,et al.  On the minimum number of templates required for shift, rotation and size invariant pattern recognition , 1988, Pattern Recognit..

[8]  Yung-Sheng Chen,et al.  A modified fast parallel algorithm for thinning digital patterns , 1988, Pattern Recognit. Lett..

[9]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[10]  Abhay B. Bulsari,et al.  Some analytical solutions to the general approximation problem for feedforward neural networks , 1993, Neural Networks.

[11]  Paulo J. G. Lisboa,et al.  Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers , 1992, IEEE Trans. Neural Networks.

[12]  T. Caelli,et al.  Implications of spatial summation models for processes of contour perception: a geometric perspective , 1978, Vision Research.

[13]  Marvin Minsky,et al.  An introduction to computational geometry , 1969 .

[14]  David A. Forsyth,et al.  Transformational invariance - a primer , 1990, BMVC.

[15]  D. Casasent,et al.  Position, rotation, and scale invariant optical correlation. , 1976, Applied optics.

[16]  Hiroshi Murase,et al.  A lie group theoretic approach to the invariance problem in feature extraction and object recognition , 1991, Pattern Recognit. Lett..

[17]  Stan Z. Li,et al.  Matching: Invariant to translations, rotations and scale changes , 1992, Pattern Recognit..

[18]  Etienne Barnard,et al.  Backpropagation uses prior information efficiently , 1993, IEEE Trans. Neural Networks.

[19]  W. Hoffman.  The Lie algebra of visual perception , 1966 .

[20]  E. Dubois,et al.  Digital picture processing , 1985, Proceedings of the IEEE.

[21]  Saturnino L. Salas.  Calculus : one and several variables with analytic geometry / Saturnino L. Salas , 1974 .

[22]  Andrew Zisserman,et al.  Introduction—towards a new framework for vision , 1992 .

[23]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[24]  Terry Caelli,et al.  Model-based neural networks , 1993, Neural Networks.

[25]  Eamon B. Barrett,et al.  Representation of Three-Dimensional Object Structure as Cross-Ratios of Determinants of Stereo Image Points , 1993, Applications of Invariance in Computer Vision.

[26]  Terry Caelli,et al.  Shift, rotation and scale invariant signatures for two-dimensional contours, in a neural network architecture , 1997 .

[27]  Warren S. Sarle,et al.  Neural Networks and Statistical Models , 1994 .

[28]  Jürgen Altmann,et al.  A Fast Correlation Method for Scale-and Translation-Invariant Pattern Recognition , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Yehoshua Y. Zeevi,et al.  The Canonical Coordinates Method for Pattern Deformation: Theoretical and Computational Considerations , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Alireza Khotanzad,et al.  Classification of invariant image representations using a neural network , 1990, IEEE Trans. Acoust. Speech Signal Process..

[31]  M. Ferraro,et al.  Relationship between integral transform invariances and Lie group theory , 1988 .

[32]  M. Ferraro,et al.  Lie transformation groups, integral transforms, and invariant pattern recognition. , 1994, Spatial vision.

[33]  T Caelli,et al.  Orientation-position coding and invariance characteristics of pattern discrimination , 1984, Perception & psychophysics.

[34]  Reiner Lenz,et al.  Group invariant pattern recognition , 1990, Pattern Recognit..

[35]  Feng Lin,et al.  Towards absolute invariants of images under translation, rotation, and dilation , 1993, Pattern Recognit. Lett..

[36]  Yehoshua Y. Zeevi,et al.  Recognition of distorted patterns by invariance kernels , 1991, Pattern Recognit..

[37]  Xiaobo Li,et al.  Towards a system for automatic facial feature detection , 1993, Pattern Recognit..

[38]  Anil K. Jain.  Fundamentals of Digital Image Processing , 2018, Control of Color Imaging Systems.

[39]  Michael J. Swain,et al.  Indexing via color histograms , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[40]  H. Barrow,et al.  Computational vision , 1981, Proceedings of the IEEE.

[41]  L. Gool,et al.  Semi-differential invariants , 1992 .

[42]  Aggelos K. Katsaggelos,et al.  Edge detection using a neural network , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[43]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[44]  David A. Pintsov.  Invariant pattern recognition, symmetry, and Radon transforms , 1989 .