A
CMOS implementation of the R-transform for translation invariant
feature extraction
- Spencer, R.G.; Sanchez-Sinencio, E.
Editor(s): Ramirez-Angulo, J.
Analog & Mixed-Signal Center, Texas A&M; Univ., College
Station, TX, USA
This paper appears in: Circuits and Systems, 2000.
42nd Midwest Symposium on
On page(s): 556 - 558 vol. 1
8-11 Aug. 1999
Las Cruces, NM, USA
2000
Volume: 1
ISBN: 0-7803-5491-5
IEEE Catalog Number: 99CH36356
Number of Pages: 2 vol. (xl+1150)
References Cited: 3
INSPEC Accession Number: 6788780
Abstract:
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.
Index Terms:
CMOS integrated circuits; VLSI; feature extraction; transforms;
image recognition; CMOS implementation; R-transform; translation
invariant feature extraction; spatially distributed analog inputs;
image rows; image columns