A CMOS implementation of the R-transform for translation invariant feature extraction

A CMOS implementation of the R-transform for translation invariant feature extraction

A CMOS implementation of a one-dimensional R-transform with 32 inputs is presented. The implementation generates a translation invariant feature vector from a set of spatially distributed analog inputs. Repeated application to the rows and columns of an image achieves two-dimensional translation inv...

Full description

Saved in:
Bibliographic Details
Published in:42nd Midwest Symposium on Circuits and Systems (Cat. No.99CH36356) Vol. 1; pp. 556 - 558 vol. 1
Main Authors: Spencer, R.G., Sanchez-Sinencio, E.
Format: Conference Proceeding
Language:English
Published: IEEE 1999
Subjects:
Cameras
Circuits
Fast Fourier transforms
Feature extraction
Indium phosphide
Large scale integration
Pattern recognition
Transfer functions
Very large scale integration
Voltage
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A CMOS implementation of a one-dimensional R-transform with 32 inputs is presented. The implementation generates a translation invariant feature vector from a set of spatially distributed analog inputs. Repeated application to the rows and columns of an image achieves two-dimensional translation invariance. Results are presented that demonstrate the translation invariance.
ISBN:0780354915
9780780354913
DOI:10.1109/MWSCAS.1999.867327