Because of the increasing influence it has in image watermarking applications, the estimation of the distribution shape of full frame DCT coefficients is here addressed. Based on previous analyses on block-DCT, the coefficients are first assumed to follow a Generalized Gaussian distribution. The shape parameter is then evaluated according to the maximum likelihood criterion applied to a set of 170 natural images. The analysis has been further validated by using the 2 test-of-t criterion. In contrast to the block-DCT case, experimental results prove that full frame DCT coefficients can be modeled without appreciable loss of performance by a Laplacian density function having variance decreasing with frequency.
Statistical modelling of full-frame DCT coefficients / Barni, M.; Bartolini, F.; Piva, A.; Rigacci, F.. - STAMPA. - 3:(1998), pp. 1513-1516. (Intervento presentato al convegno European Signal Processing Conference EUSIPCO 98 tenutosi a Island of Rhodes, Greece nel September 8-11, 199).
Statistical modelling of full-frame DCT coefficients
PIVA, ALESSANDRO;
1998
Abstract
Because of the increasing influence it has in image watermarking applications, the estimation of the distribution shape of full frame DCT coefficients is here addressed. Based on previous analyses on block-DCT, the coefficients are first assumed to follow a Generalized Gaussian distribution. The shape parameter is then evaluated according to the maximum likelihood criterion applied to a set of 170 natural images. The analysis has been further validated by using the 2 test-of-t criterion. In contrast to the block-DCT case, experimental results prove that full frame DCT coefficients can be modeled without appreciable loss of performance by a Laplacian density function having variance decreasing with frequency.I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.