论文信息 - Boosting OCR Classifier by Optimal Edge Noise Filtering

Boosting OCR Classifier by Optimal Edge Noise Filtering

The problem of Optical Character Recognition (OCR) can be solved by set operators implemented as programs for a Morphological Machine (MMach). In this paper, we present two techniques to boost such programs: (1) Anchoring and (2) Edge Noise Filtering by Stamp. The power of these techniques is demonstrated by some impressive experimental results.

Edward R. Dougherty | Junior Barrera | Marcel Brun | Routo Terada

[1] G. Banon,et al. Minimal representations for translation-invariant set mappings by mathematical morphology , 1991 .

[2] Jean Serra,et al. Image Analysis and Mathematical Morphology , 1983 .

[3] Edward R. Dougherty,et al. Optimal iterative increasing binary morphological filters , 1996 .

[4] Junior Barrera,et al. Expressiveness of the morphological language , 1992, Optics & Photonics.

[5] Junior Barrera,et al. Automatic Programming of MMach's for OCR , 1996, ISMM.

[6] Edward R. Dougherty,et al. Automatic programming of binary morphological machines by design of statistically optimal operators in the context of computational learning theory , 1997, J. Electronic Imaging.

[7] Junior Barrera,et al. Set operations on closed intervals and their applications to the automatic programming of morphological machines , 1996, J. Electronic Imaging.

[8] Junior Barrera,et al. OCR based on mathematical morphology , 1998, Electronic Imaging.