In some industrial optical character recognition applications, the background of the image surrounding the characters is very confusing and contains clutter that often overlays and connects the characters. Characters are found amidst the clutter by applying a number of morphological structuring elements to the image. Each structuring element is responsible for locating a specific class of characters where all characters in that class are similar to each other. The set of all structuring elements efficiently covers the entire character set. To further reduce noise, other checks such as colinearity and equidistance of the characters in the string are applied. This paper describes an automatic training method for defining efficient classes of structuring elements.
Training of object classes using mathematical morphology
Nonlinear Image Processing III ; 1992 ; San Jose,CA,United States
Proc. SPIE ; 1658
1992-04-01
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Bitslice Noise Reduction Using Mathematical Morphology
British Library Online Contents | 1997
|Hypercomplex Mathematical Morphology
British Library Online Contents | 2011
|Spatially-Variant Mathematical Morphology
British Library Conference Proceedings | 1994
|Remote Bar Code Localisation Using Mathematical Morphology
British Library Conference Proceedings | 1999
|Locally adaptable mathematical morphology
IEEE | 2005
|