The edge detection problem in blurred and noisy 2-D signals is dealt with. An adaptive signal processing algorithm is proposed which marks edge points according to an hypothesis test which compares the likelihoods of two models describing the local signal behaviour in the two cases of absence/presence of an edge. The two models are identi"ed by a regularized least squares estimation algorithm, obtaining a numerically e$cient procedure, quite robust with respect to additive noise and blurr perturbation. No global thresholding or data pre"ltering is required
Bayesian Estimation of edges in blurred and noisy images / DE SANTIS, Alberto; DI LEO, A.; Iacoviello, Daniela. - STAMPA. - (1999), pp. 655-668. (Intervento presentato al convegno Communication and Control Conference tenutosi a Atene).
Bayesian Estimation of edges in blurred and noisy images
DE SANTIS, Alberto;IACOVIELLO, Daniela
1999
Abstract
The edge detection problem in blurred and noisy 2-D signals is dealt with. An adaptive signal processing algorithm is proposed which marks edge points according to an hypothesis test which compares the likelihoods of two models describing the local signal behaviour in the two cases of absence/presence of an edge. The two models are identi"ed by a regularized least squares estimation algorithm, obtaining a numerically e$cient procedure, quite robust with respect to additive noise and blurr perturbation. No global thresholding or data pre"ltering is requiredI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
