Neural network model for rotation invariant recognition of object shapes.

A multichannel, multilayer feed forward neural network model is proposed for rotation invariant recognition of objects. In the M channel network, each channel consists of a one dimensional slice of the two dimensional (2D) Fourier transform (FT) of the input pattern that connects fully to the weight matrix. Each slice is taken at different angles from the 2D FT of the object. From each channel, only one neuron can fire in the presence of the training object. The output layer sums up the response of the hidden layer neuron and confirms the presence of the object. Rotation invariant recognition from 0 degrees to 360 degrees is obtained even in the case of degraded images.

[1]  Mingshi Wang,et al.  Rotation- and scale-invariant texture features based on spectral moment invariants. , 2007, Journal of the Optical Society of America. A, Optics, image science, and vision.

[2]  D. Casasent,et al.  Minimum average correlation energy filters. , 1987, Applied optics.

[3]  Chris Chatwin,et al.  Position, rotation, scale, and orientation invariant multiple object recognition from cluttered scenes , 2005, SPIE Defense + Commercial Sensing.

[4]  Naveen K Nishchal,et al.  Wavelet-modified maximum average correlation height filter for rotation invariance that uses chirp encoding in a hybrid digital-optical correlator. , 2006, Applied optics.

[5]  David Casasent,et al.  A hierarchical classifier using new support vector machines for automatic target recognition , 2005, Neural Networks.

[6]  Ning Wu,et al.  Rotationally invariant pattern recognition by use of linear and nonlinear cascaded filters. , 2005, Applied optics.

[7]  B. V. K. Vijaya Kumar,et al.  Optimal tradeoff circular harmonic function correlation filter methods providing controlled in-plane rotation response , 2000, IEEE Trans. Image Process..

[8]  V R Riasati,et al.  Projection-slice synthetic discriminant functions for optical pattern recognition. , 1997, Applied optics.

[9]  B. V. Vijaya Kumar,et al.  Unconstrained correlation filters. , 1994, Applied optics.

[10]  B. V. Kumar,et al.  Linear phase coefficient composite filter banks for distortion-invariant optical pattern recognition , 1990 .

[11]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[12]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[13]  D Casasent,et al.  Multivariant technique for multiclass pattern recognition. , 1980, Applied optics.

[14]  H H Arsenault,et al.  Properties of the circular harmonic expansion for rotation-invariant pattern recognition. , 1986, Applied optics.