What people are saying - Write a review
We haven't found any reviews in the usual places.
several image recognition problems using the parametric models defined
A Parametric Model of the ImageGenerating Process
9 other sections not shown
Other editions - View all
admissible transformations algorithm approximation arbitrary archetype Bayesian Chapter character reader column components conditional entropy constraints constructed convex convex function corresponding criterion decision function defined denote depends described digitized discriminant functions distribution p(v documents edges elementary images elementary prototype elementary similarities error probability estimate expanded graph field of view formulation given image gray shade Hamming distance image classes image recognition initial learning problem likelihood function linear subspace machine maximal maximum similarity maximum-likelihood noise normal distribution nuisance parameter observed image obtained optical optical correlator optimal decision optimal path parametric model pattern recognition perceptron photodiodes piecewise linear posterior distribution posterior probabilities potentially optimal probability distribution quantization quasiconvex random variable recognition parameter recognition problem recognized retina retina cell Section self-learning sequence shown in Figure solution solve statistical subset symbols templates terminal symbols training sample translation type graph vector vertex vertices width window