Focal Plane Implementation of 2D Steerable and Scalable Gabor-Type Filters

We describe the analog CMOS VLSI implementation of a cellular neural network (CNN) architecture which spatially filters a 2D image by two orientation selective image filters. The image is represented by a set of input currents supplied by an on-chip array of photosensors. The filters are similar to even and odd Gabor filters. The CNN architecture is implemented using two resistive networks coupled by transconductance amplifiers. The tuned orientation can be steered and the filter response scaled by adjusting the conductances of the resistors and gains of the transconductance amplifiers through externally supplied bias voltages. The circuit operation is explained via a variational principle, which defines the filter output as the minimum of a cost function. We report test results from both 25 × 25 and 45 × 45 pixel arrays.

[1]  Carver A. Mead,et al.  Scanners for visualizing activity of analog VLSI circuitry , 1991 .

[2]  K. W. Cattermole.  The Fourier Transform and its Applications , 1965 .

[3]  Bertram E. Shi.  Subthreshold Current Mode Design of Gabor-type CNN Image Filters , 1999 .

[4]  Leon O. Chua,et al.  The CNN paradigm , 1993 .

[5]  Daniele D. Caviglia,et al.  Artificial visual orientation map implemented as an inhomogeneous active resistor mesh , 1993 .

[6]  Si-Chen Lee,et al.  Amorphous silicon four quadrant orientation detector (FOQUOD) for application to neural network image sensors , 1990, International Technical Digest on Electron Devices.

[7]  Bertram E. Shi.  A one-dimensional CMOS focal plane array for Gabor-type image filtering , 1999 .

[8]  Jan Van der Spiegel,et al.  A silicon VLSI optical sensor for pattern recognition , 1994 .

[9]  Luigi Raffo,et al.  An Analog VLSI Computational Engine for Early Vision Tasks , 1997, ICANN.

[10]  C. Westin,et al.  Phase-based Disparity Estimation , 1995 .

[11]  Bertram E. Shi.  Gabor-type image filtering with cellular neural networks , 1996, 1996 IEEE International Symposium on Circuits and Systems. Circuits and Systems Connecting the World. ISCAS 96.

[12]  Luigi Raffo.  Resistive network implementing maps of Gabor functions of any phase , 1995 .

[13]  Daniele D. Caviglia,et al.  Anisotropic active resistor meshes for implementing image processing operators , 1993 .

[14]  J. Daugman.  Two-dimensional spectral analysis of cortical receptive field profiles , 1980, Vision Research.

[15]  Stephen Grossberg,et al.  A solution of the figure-ground problem for biological vision , 1993, Neural Networks.

[16]  Jan Van der Spiegel,et al.  A compact line and edge orientation detection sensor , 1994 .

[17]  T Lourens,et al.  Biologically Motivated Approach to Face Recognition , 1993, IWANN.

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

[19]  Eric A. Vittoz,et al.  An integrated cortical layer for orientation enhancement , 1997 .

[20]  Bertram E. Shi,et al.  An Analog VLSI Neural Network for Phase-based Machine Vision , 1997, NIPS.

[21]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

[22]  Ralph Etienne-Cummings,et al.  A General Purpose Image Processing Chip: Orientation Detection , 1997, NIPS.

[23]  Berthold K. P. Horn,et al.  An object position and orientation IC with embedded imager , 1991 .

[24]  Bertram E. Shi.  USING A CNN SENSOR FOR 1D IMAGE FIXATION , 1998 .

[25]  A. Rodriguez-Vazquez,et al.  CNNUC3: a mixed-signal 64/spl times/64 CNN universal chip , 1999, Proceedings of the Seventh International Conference on Microelectronics for Neural, Fuzzy and Bio-Inspired Systems.

[26]  David J. Fleet.  Measurement of image velocity , 1992 .

[27]  T. Serrano-Gotarredona,et al.  A 2D image filtering architecture for real-time vision processing systems , 1999, Proceedings of the Seventh International Conference on Microelectronics for Neural, Fuzzy and Bio-Inspired Systems.

[28]  Gert Cauwenberghs,et al.  Analog VLSI Cellular Implementation of the Boundary Contour System , 1998, NIPS.

[29]  T. Poggio,et al.  Ill-posed problems in early vision: from computational theory to analogue networks , 1985, Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.

[30]  Luigi Raffo,et al.  Synthesis of a recurrent double-layer transistor network for early-vision tasks , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).

[31]  Ángel Rodríguez-Vázquez,et al.  CMOS optical-sensor array with high output current levels and automatic signal-range centring , 1994 .

[32]  Bertram E. Shi,et al.  Gabor-type filtering in space and time with cellular neural networks , 1998 .

[33]  David J. Fleet,et al.  Phase-based disparity measurement , 1991, CVGIP Image Underst..

[34]  Hanspeter A. Mallot,et al.  Phase-based binocular vergence control and depth reconstruction using active vision , 1994 .

[35]  Ralph Etienne-Cummings,et al.  Neuromorphic vision sensors , 1996 .

[36]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[37]  M. Porat,et al.  Localized texture processing in vision: analysis and synthesis in the Gaborian space , 1989, IEEE Transactions on Biomedical Engineering.

[38]  M. Conti,et al.  High-frequency fully differential filter using operational amplifiers without common-mode feedback , 1989 .