CMOS rotation-invariant pattern recognition system

Author

Chiu, Chin-Fong ; Wu, Chung-Yu

Author_Institution

Integrated Circuit & Syst. Lab., Nat. Chiao Tung Univ., Hsinchu, Taiwan

fYear

1996

fDate

18-21 Nov 1996

Firstpage

516

Lastpage

519

Abstract

A new rotation-invariant pattern recognition system is proposed and analyzed. In this system, silicon retina cells capable of image sensing and edge extraction are used so that the system can directly process images from the real world without an extra edge detector. The rotation-invariant discrete correlation function is modified and implemented in the silicon retina structure by using current summation. Simulation results have verified the correct function of the proposed system. Moreover, an experimental chip to implement the proposed system with a 32×32 cell array has been designed and fabricated in a 0.8 μm N-well CMOS process. Experimental results have successfully shown that the system works well for arbitrary orientation pattern recognition

Keywords

CMOS digital integrated circuits; circuit analysis computing; computer vision; correlation methods; digital signal processing chips; edge detection; image processing equipment; image recognition; image sensors; 0.8 mum; 32×32 cell array; CMOS rotation-invariant pattern recognition system; N-well CMOS process; arbitrary orientation pattern recognition; current summation; discrete circular harmonic transformation; edge extraction; image sensing; machine vision; rotation-invariant discrete correlation function; silicon retina cells; simulation results; Circuits; Decoding; Digital images; Image edge detection; Latches; Pattern recognition; Phototransistors; Pixel; Retina; Silicon;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1996., IEEE Asia Pacific Conference on

Conference_Location

Seoul

Print_ISBN

0-7803-3702-6

Type

conf

DOI

10.1109/APCAS.1996.569327

Filename

569327