A Scalable FPGA Implementation of Cellular Neural Networks for Gabor-type Filtering

We describe an implementation of Gabor-type filters on field programmable gate arrays using the cellular neural network (CNN) architecture. The CNN template depends upon the parameters (e.g., orientation, bandwidth) of the Gabor-type filter and can be modified at runtime so that the functionality of...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheung, O.Y.H., Leong, P.H.W., Tsang, E.K.C., Shi, B.E.
Format: Conference Proceeding
Language:English
Subjects:
Biological system modeling
Biology computing
Biomedical signal processing
Cellular neural networks
Energy consumption
Field programmable gate arrays
Gabor filters
Retina
Very large scale integration
Visual system
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We describe an implementation of Gabor-type filters on field programmable gate arrays using the cellular neural network (CNN) architecture. The CNN template depends upon the parameters (e.g., orientation, bandwidth) of the Gabor-type filter and can be modified at runtime so that the functionality of Gabor-type filter can be changed dynamically. Our implementation uses the Euler method to solve the ordinary differential equation describing the CNN. The design is scalable to allow for different pixel array sizes, as well as simultaneous computation of multiple filter outputs tuned to different orientations and bandwidths. For 1024 pixel frames, an implementation on a Xilinx Virtex XC2V1000-4 device uses 1842 slices, operates at 120 MHz and achieves 23,000 Euler iterations over one frame per second.
ISSN:2161-4393
2161-4407
DOI:10.1109/IJCNN.2006.246653