IMAGE RECOGNITION USING PARALLEL FEATURE EXTRACTION AND 2D FOURIER TRANSFORM

  • POPESCU CORNEL
    University “POLITEHNICA” of Bucharest, Splaiul Independentei 313, Sector 6, Bucharest, 060042, Romania
  • CULEA GEORGE
    “Vasile Alecsandri” University of Bacău, Calea Mărăşeşti 156,Bacău, 600115, Romania

Abstract

This paper presents an efficient algorithm for matching images. It is part of a bigger, ongoing research, which aims a full facial recognition system. The main goals of this project are the use of deterministic methods to obtain the solution. The present algorithm can provide an alternative to the legacy sum-of-absolute-differences (SAD) based methods used in the motion picture processing industry.

Cuvinte cheie

image recognition Fourier transform MPI parallelization