论文信息 - DESIGN OF A PIXEL-PARALLEL FEATURE EXTRACTION VLSI SYSTEM FOR BIOLOGICALLY-INSPIRED OBJECT RECOGNITION METHODS

DESIGN OF A PIXEL-PARALLEL FEATURE EXTRACTION VLSI SYSTEM FOR BIOLOGICALLY-INSPIRED OBJECT RECOGNITION METHODS

This paper proposes a biologically-inspired feature extraction method, which consists of coarse region segmentation by a resistive-fuse network and feature extraction by Gabor wavelet transforms. Their pixel-parallel VLSI implementation based on the pulse modulation circuit architecture is described, and measurement results of Gabor filter operation by a test LSI chip with 1-D 20-pixels are presented.

[1] Carver Mead,et al. Analog VLSI and neural systems , 1989 .

[2] Makoto Nagata,et al. A concept of analog-digital merged circuit architecture for future VLSI's , 1996 .

[3] Bertram E. Shi. 2D focal plane steerable and scalable cortical filters [image sensor] , 1999, Proceedings of the Seventh International Conference on Microelectronics for Neural, Fuzzy and Bio-Inspired Systems.

[4] Makoto Nagata,et al. A Nonlinear oscillator network for Gray-level image segmentation and PWM/PPM circuits for its VLSI implementation , 2000 .

[5] Mitsumasa Koyanagi,et al. Smart Vision Chip Fabricated Using Three Dimensional Integration Technology , 2000, NIPS.

[6] Makoto Miyake,et al. A Multi-Functional Cellular Neural Network Circuit Using Pulse Modulation Signals for Image Recognition , 2000 .

[7] Makoto Miyake,et al. A 1-D CMOS PWM Cellular Neural Network Circuit and Resistive-Fuse Network Operation , 2001 .