In this paper, a new fractal based recognition method, Face Authentication using Speed Fractal Technique (FAST), is presented. The main contribution is the good compromise between memory requirements, execution time and recognition ratio. FAST is based on Iterated Function Systems (IFS) theory, largely studied in still image compression and indexing, but not yet widely used for face recognition. Indeed, Fractals are well known to be invariant to a large set of global transformations. FAST is robust with respect to meaningful variations in facial expression and to the small changes of illumination and pose. Another advantage of the FAST strategy consists in the speed up that it introduces. The typical slowness of fractal image compression is avoided by exploiting only the indexing phase, which requires time O(D log (D)), where D is the size of the domain pool. Lastly, the FAST algorithm compares well to a large set of other recognition methods, as underlined in the experimental results.

Face Authentication using Speed Fractal Technique

ABATE, Andrea Francesco;NAPPI, Michele;DISTASI, Riccardo;RICCIO, DANIEL
2006

Abstract

In this paper, a new fractal based recognition method, Face Authentication using Speed Fractal Technique (FAST), is presented. The main contribution is the good compromise between memory requirements, execution time and recognition ratio. FAST is based on Iterated Function Systems (IFS) theory, largely studied in still image compression and indexing, but not yet widely used for face recognition. Indeed, Fractals are well known to be invariant to a large set of global transformations. FAST is robust with respect to meaningful variations in facial expression and to the small changes of illumination and pose. Another advantage of the FAST strategy consists in the speed up that it introduces. The typical slowness of fractal image compression is avoided by exploiting only the indexing phase, which requires time O(D log (D)), where D is the size of the domain pool. Lastly, the FAST algorithm compares well to a large set of other recognition methods, as underlined in the experimental results.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11386/1527493
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 5
social impact