A PWM-Mode Pixel-Parallel Image-Processing Circuit Performing Directional State-Propagation and Its Application to Subjective Contour Generation

As an approach to constructing highly organized and intelligent image recognition systems mimicking the visual architecture in the human brain, we have designed an image processing circuit that performs a directional pixel-state propagation algorithm based on a pixel-parallel architecture using pulse-width modulation (PWM) signals. Directional pixel-state propagation can be used for subjective contour generation, which is a typical function of the visual system in the human brain to fill gaps in natural-image information. A PWM-mode circuit can provide more compact circuit configuration than digital circuits, and can achieve focal-plane analog processing by combining with image sensors without A/D converters. Such circuits are suitable for repetitive algorithms, which require offset-free arithmetic. The proof-of-concept LSI chip has been designed and fabricated using a 0.25 $$\upmu $$μm mixed-signal CMOS process. There are 35 $$\times $$× 35 processing units included in the chip, the operation cycle time for propagation step is 2.2 $$\upmu $$μs, and the power consumption is 363 mW at a supply voltage of 3.3 V. In experiments using this LSI chip, we have successfully generated subjective contours of Kanizsa figures.

[1]  Takashi Morie,et al.  Pulse Modulation Techniques for Nonlinear Dynamical Systems and a CMOS Chaos Circuit with Arbitrary 1-D Maps , 2004 .

[2]  Mitsumasa Koyanagi,et al.  High-Density Through Silicon Vias for 3-D LSIs , 2009, Proceedings of the IEEE.

[3]  Tadashi Shibata,et al.  A Pixel-Parallel Self-Similitude Processing for Multiple-Resolution Edge-Filtering Analog Image Sensors , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[4]  Ángel Rodríguez-Vázquez,et al.  ACE16k: A Programmable Focal Plane Vision Processor with 128 x 128 Resolution , 2001 .

[5]  T. Morie,et al.  A pixel-parallel image processor for Gabor filtering based on merged analog/digital architecture , 2004, 2004 Symposium on VLSI Circuits. Digest of Technical Papers (IEEE Cat. No.04CH37525).

[6]  Daniel Matolin,et al.  A QVGA 143 dB Dynamic Range Frame-Free PWM Image Sensor With Lossless Pixel-Level Video Compression and Time-Domain CDS , 2011, IEEE Journal of Solid-State Circuits.

[7]  Ángel Rodríguez-Vázquez,et al.  Power-efficient focal-plane image representation for extraction of enriched Viola-Jones features , 2012, 2012 IEEE International Symposium on Circuits and Systems.

[8]  Takashi Morie,et al.  A subjective-contour generation LSI system with expandable pixel-parallel architecture for vision systems , 2009, 2009 IEEE International Solid-State Circuits Conference - Digest of Technical Papers.

[9]  Takashi Morie,et al.  A pixel-parallel anisotropic diffusion algorithm for subjective contour generation , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[10]  D. S. Wills,et al.  Smart CMOS focal plane arrays: a Si CMOS detector array and sigma-delta analog-to-digital converter imaging system , 1999 .

[11]  Daphne Maurer,et al.  The development of contour interpolation: evidence from subjective contours. , 2010, Journal of experimental child psychology.

[12]  Ángel Rodríguez-Vázquez,et al.  A 0.8-μm CMOS two-dimensional programmable mixed-signal focal-plane array processor with on-chip binary imaging and instructions storage , 1997, IEEE J. Solid State Circuits.

[13]  K. Kondo,et al.  Through Silicon Via , 2014 .

[14]  Makoto Motoyoshi,et al.  Through-Silicon Via (TSV) , 2009, Proceedings of the IEEE.

[15]  Atsushi Iwata,et al.  Merged Analog-Digital Circuits Using Pulse Modulation for Intelligent SoC Applications , 2001 .

[16]  A. Paasio,et al.  An 8$\times$ 8 Cell Analog Order-Statistic-Filter Array With Asynchronous Grayscale Morphology in 0.13-$\mu{\hbox{m}}$ CMOS , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[17]  Ralph Etienne-Cummings,et al.  A programmable focal-plane MIMD image processor chip , 2001, IEEE J. Solid State Circuits.

[18]  Takashi Morie,et al.  A Pixel Circuit Implementing an Anisotropic Diffusion Algorithm for Subjective Contour Generation Using Merged Analog-Digital Approach (Special Section on Papers Awarded the Student Paper Award at NCSP'06) , 2006 .

[19]  István Petrás,et al.  A bio-inspired two-layer mixed-signal flexible programmable chip for early vision , 2003, IEEE Trans. Neural Networks.

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

[21]  P. Dudek.  Adaptive sensing and image processing with a general-purpose pixel-parallel sensor/processor array integrated circuit , 2007, 2006 International Workshop on Computer Architecture for Machine Perception and Sensing.

[22]  Tülay Yildirim,et al.  A Mixed Mode Neural Network Circuitry for Object Recognition Application , 2013, Circuits Syst. Signal Process..

[23]  István Petrás,et al.  Second-order neural core for bioinspired focal-plane dynamic image processing in CMOS , 2004, IEEE Transactions on Circuits and Systems I: Regular Papers.

[24]  Ricardo Carmona-Galán,et al.  FLIP-Q: A QCIF Resolution Focal-Plane Array for Low-Power Image Processing , 2011, IEEE Journal of Solid-State Circuits.

[25]  Piotr Dudek,et al.  A general-purpose processor-per-pixel analog SIMD vision chip , 2005, IEEE Transactions on Circuits and Systems I: Regular Papers.

[26]  Ari Paasio,et al.  MIPA4k: A 64×64 cell mixed-mode image processor array , 2009, 2009 IEEE International Symposium on Circuits and Systems.

[27]  Antonio Petraglia,et al.  CMOS Imager With Focal-Plane Analog Image Compression Combining DPCM and VQ , 2013, IEEE Transactions on Circuits and Systems I: Regular Papers.