Image Pattern Recognition
During the last twenty years the problem of pattern recognition (specifically, image recognition) has been studied intensively by many investigators, yet it is far from being solved. The number of publications increases yearly, but all the experimental results-with the possible exception of some dealing with recognition of printed characters-report a probability of error significantly higher than that reported for the same images by humans. It is widely agreed that ideally the recognition problem could be thought of as a problem in testing statistical hypotheses. However, in most applications the immediate use of even the simplest statistical device runs head on into grave computational difficulties, which cannot be eliminated by recourse to general theory. We must accept the fact that it is impossible to build a universal machine which can learn an arbitrary classification of multidimensional signals. Therefore the solution of the recognition problem must be based on a priori postulates (concerning the sets of signals to be recognized) that will narrow the set of possible classifications, i.e., the set of decision functions. This notion can be taken as the methodological basis for the approach adopted in this book.
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
11 other sections not shown
Other editions - View all
according admissible algorithm allows applications approximation arbitrary assume bound called cells Chapter characters column components conditional consider consists constructed containing correlation corresponding decision rule defined definition denote depends described difficult digitized discriminant functions distance distribution documents edges elementary prototype entropy equal error probability estimate example expression fact Figure fixed formulation function given graph gray shade increases independent initial input instance known learning likelihood linear machine maximal maximum mean measure method noise normal nuisance parameter observed obtained optimal parameters portion position possible potentially practical problem quantities random reader reading recognition recognition problem recognized represented respect retina satisfy sequence shown signal similarity single solution solve space statistical step suppose symbols templates transformations translation values variable various vector vertex vertices window