Investigations On The Development Of An Ann Model & Visual Manipulation Approach For 2-D Dft Computation In Image Processing

This thesis is an outcome of the investigations carried out on the development of an Artificial Neural Network (ANN) model to implement 2-D DFT at high speed. A new definition of 2-D DFT relation is presented. This new definition enables DFT computation organized in stages involving only real addition except at the final stage of computation. The number of stages is always fixed at 4. Two different strategies are proposed. 1) A visual representation of 2-D DFT coefficients. 2) A neural network approach. The visual representation scheme can be used to compute, analyze and manipulate 2­ D signals such as images in the frequency domain in terms of symbols derived from 2x2 DFT. This, in turn, can be represented in terms of real data. This approach can help analyze signals in the frequency domain even without computing the DFT coefficients. A hierarchical neural network model is developed to implement 2-D DFT. Presently, this model is capable of implementing 2-D DFT for a particular order N such that ((N))4 = 2. The model can be developed into one that can implement the 2-D DFT for any order N upto a set maximum limited by the hardware constraints. The reported method shows a potential in implementing the 2-D DF T in hardware as a VLSI / ASIC.

[1]  J.G. Delgado-Frias,et al.  Spin-L: sequential pipelined neuroemulator with learning capabilities , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[2]  R. Singleton,et al.  A method for computing the fast Fourier transform with auxiliary memory and limited high-speed storage , 1967, IEEE Transactions on Audio and Electroacoustics.

[3]  Peter D. Welch,et al.  Historical notes on the fast Fourier transform , 1967 .

[4]  Á. Rodríguez-Vázquez,et al.  Current-mode techniques for the implementation of continuous- and discrete-time cellular neural networks , 1993 .

[5]  Shun-ichi Amari,et al.  Mathematical foundations of neurocomputing , 1990, Proc. IEEE.

[6]  Bernard Widrow,et al.  Neural nets for adaptive filtering and adaptive pattern recognition , 1988, Computer.

[7]  K. Fukushima.  Neural network model for selective attention in visual pattern recognition and associative recall. , 1987, Applied optics.

[8]  H. Wallinga,et al.  70 input, 20 nanosecond pattern classifier , 1993, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[9]  Tsuban Chen,et al.  The past, present, and future of image and multidimensional signal processing , 1998, IEEE Signal Process. Mag..

[10]  Izidor Gertner.  A new efficient algorithm to compute the two-dimensional discrete Fourier transform , 1988, IEEE Trans. Acoust. Speech Signal Process..

[11]  Vipin Kumar,et al.  The Scalability of FFT on Parallel Computers , 1993, IEEE Trans. Parallel Distributed Syst..

[12]  Yang Dekun.  Fast computation of two-dimensional discrete Fourier transform using fast discrete Radon transform , 1990, IEEE TENCON'90: 1990 IEEE Region 10 Conference on Computer and Communication Systems. Conference Proceedings.

[13]  J. A. Nossek,et al.  Winner-take-all cellular neural networks , 1993 .

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

[15]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[16]  Mahmoud K. Habib,et al.  A digital neuron-type processor and its VLSI design , 1989 .

[17]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[18]  Chwen-Jye Ju.  Equivalent relationship and unified indexing of FFT algorithm , 1993, 1993 IEEE International Symposium on Circuits and Systems.

[19]  John G. Proakis,et al.  Digital Signal Processing: Principles, Algorithms, and Applications , 1992 .

[20]  D. O. Hebb,et al.  The organization of behavior , 1988 .

[21]  P. Ienne.  Quantitative comparison of architectures for digital neuro-computers , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[22]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[23]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[24]  K Fukushima,et al.  Handwritten alphanumeric character recognition by the neocognitron , 1991, IEEE Trans. Neural Networks.

[25]  Charles M. Rader,et al.  Number theory in digital signal processing , 1979 .

[26]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[27]  R. Singleton.  An algorithm for computing the mixed radix fast Fourier transform , 1969 .

[28]  Fukumi,et al.  A new back-propagation algorithm with coupled neuron , 1989 .

[29]  A. A. Mullin,et al.  Principles of neurodynamics , 1962 .

[30]  N. Ahmed,et al.  FAST TRANSFORMS, algorithms, analysis, applications , 1983, Proceedings of the IEEE.

[31]  Santosh S. Venkatesh,et al.  The capacity of the Hopfield associative memory , 1987, IEEE Trans. Inf. Theory.

[32]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[33]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[34]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[35]  Arun N. Netravali,et al.  Digital Pictures: Representation and Compression , 1988 .

[36]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[37]  M. Balsi,et al.  MODA: moving object detecting architecture , 1993 .

[38]  K.-W. Shin,et al.  A VLSI architecture for parallel computation of FFT , 1990 .

[39]  G. L. Heileman,et al.  Concurrent object-oriented simulation of neural network models , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[40]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[41]  Stephen Grossberg,et al.  The ART of adaptive pattern recognition by a self-organizing neural network , 1988, Computer.

[42]  Fa-Long Luo,et al.  Applied neural networks for signal processing , 1997 .

[43]  Richard E. Blahut,et al.  Fast Algorithms for Digital Signal Processing , 1985 .

[44]  Harvey F. Silverman,et al.  Implementation of 2-D DFT algorithms on a loosely-coupled parallel system , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[45]  A. Cohen,et al.  Wavelets and Multiscale Signal Processing , 1995 .

[46]  Jozsef Csicsvari,et al.  High-speed character recognition using a dual cellular neural network architecture (CNND) , 1993 .

[47]  Lawrence D. Jackel,et al.  VLSI implementation of a neural network model , 1988, Computer.

[48]  P. Karivaratharajan.  A study on the properties of multi-dimensional Fourier transforms , 1984 .

[49]  M. A. Tan,et al.  Analog CMOS implementation of cellular neural networks , 1993 .

[50]  S. Winograd,et al.  New algorithms for the multidimensional discrete Fourier transform , 1983 .

[51]  Marshall C. Pease,et al.  An Adaptation of the Fast Fourier Transform for Parallel Processing , 1968, JACM.

[52]  Olaf Sporns,et al.  Synthetic neural modeling: the 'Darwin' series of recognition automata , 1990, Proc. IEEE.

[53]  A. Michel,et al.  Analysis and synthesis of a class of neural networks: linear systems operating on a closed hypercube , 1989 .

[54]  J. Glanz,et al.  Mastering the Nonlinear Brain , 1997, Science.

[55]  Jin Luo,et al.  Computing motion using analog and binary resistive networks , 1988, Computer.

[56]  S. Grossberg,et al.  Pattern Recognition by Self-Organizing Neural Networks , 1991 .

[57]  Edgar Sanchez-Sinencio,et al.  A current-mode cellular neural network implementation , 1993 .

[58]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[59]  P. K. Rajan.  Fast DFT algorithms for diagonally symmetric 2-D data , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[60]  H. V. Sorensen,et al.  A new efficient algorithm for computing a few DFT points , 1988, 1988., IEEE International Symposium on Circuits and Systems.

[61]  Mahalingam Ramkumar,et al.  An FFT-based technique for fast fractal image compression , 1997, Signal Process..

[62]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[63]  Jonathan S. Kane,et al.  POPART: partial optical implementation of adaptive resonance theory 2 , 1993, IEEE Trans. Neural Networks.

[64]  Norbert Fruehauf,et al.  Fourier optical realization of cellular neural networks , 1993 .

[65]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[66]  Dean A. Pomerleau,et al.  What's hidden in the hidden layers? , 1989 .

[67]  David M. Skapura,et al.  Neural networks - algorithms, applications, and programming techniques , 1991, Computation and neural systems series.

[68]  Tamás Roska,et al.  The CNN universal machine: an analogic array computer , 1993 .

[69]  Izidor Gertner,et al.  A Parallel Algorithm for 2-D DFT Computation with No Interprocessor Communication , 1990, IEEE Trans. Parallel Distributed Syst..

[70]  I. Hartimo,et al.  A novel double-decomposition method for systolic implementation of DFT , 1992, [Proceedings] 1992 IEEE International Symposium on Circuits and Systems.

[71]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[72]  Ring structure and multi-dimensional discrete Fourier transform on a power of 2 , 1992, [Proceedings] 1992 IEEE International Symposium on Circuits and Systems.

[73]  M. Akil,et al.  A reconfigurable architecture for real time segmentation of image sequences using self-organizing feature maps , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[74]  Ioannis Pitas,et al.  Parallel Algorithms for Digital Image Processing, Computer Vision and Neural Networks , 1993 .

[75]  Jack L. Meador,et al.  Programmable impulse neural circuits , 1991, IEEE Trans. Neural Networks.

[77]  E. Brigham,et al.  The fast Fourier transform and its applications , 1988 .

[78]  Wolfgang Rosenstiel,et al.  Hardware synthesis for neural networks from a behavioral description with VHDL , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[79]  Jan P. Allebach,et al.  Multidimensional Signal Processing , 1997 .

[80]  Teuvo Kohonen,et al.  The 'neural' phonetic typewriter , 1988, Computer.

[81]  S. Y. Kung,et al.  Parallel architectures for artificial neural nets , 1988, IEEE 1988 International Conference on Neural Networks.

[82]  E. Torbey,et al.  Architectural synthesis for digital neural networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[83]  Kunihiko Fukushima,et al.  A neural network for visual pattern recognition , 1988, Computer.

[84]  H.S. Chung,et al.  A novel digital multiplier chip based on the neural network , 1990, IEEE International Symposium on Circuits and Systems.

[85]  Terrence J. Sejnowski,et al.  NETtalk: a parallel network that learns to read aloud , 1988 .

[86]  Selim G. Akl,et al.  A Parallel Algorithm for Computing Fourier Transforms on the Star Graph , 1994, IEEE Trans. Parallel Distributed Syst..

[87]  H. Harrer.  Multiple layer discrete-time cellular neural networks using time-variant templates , 1993 .

[88]  Rafik Braham,et al.  The design of a neural network with a biologically motivated architecture , 1990, IEEE Trans. Neural Networks.

[89]  Mohamed I. Elmasry,et al.  The digi-neocognitron: a digital neocognitron neural network model for VLSI , 1992, IEEE Trans. Neural Networks.

[90]  Renato Stefanelli,et al.  Mapping neural nets onto a massively parallel architecture: a defect-tolerance solution , 1991, Proc. IEEE.

[91]  LiMin Fu,et al.  Rule Generation from Neural Networks , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[92]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[93]  T. Watanabe,et al.  Neural network simulation on a massively parallel cellular array processor: AAP-2 , 1989, International 1989 Joint Conference on Neural Networks.

[94]  Jacques J. Vidal.  Implementing neural nets with programmable logic , 1988, IEEE Trans. Acoust. Speech Signal Process..

[95]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[96]  Wolfgang Porod,et al.  Qualitative analysis and synthesis of a class of neural networks , 1988 .

[97]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[98]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[99]  Kunihiko Fukushima,et al.  Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position , 1982, Pattern Recognit..