| Paper Details: | Downloads: 396 |
| Serial Number: | P1150527102
|
| Title: | TRAINING OCR SYSTEMS USING VARIANTS OF IDEAL IMAGES
|
| Authors: | IBRAHIM S. I. ABUHAIBA
|
| Abstract: | This paper shows that the learning stage of highperformance
character classifiers can be achieved using
only ideal images and/or simple variants of them. We
are interested in 94 character classes of the ASCII
character set. We use a software tool to generate binary
ideal images of these characters. Ideal images are
supported with simple variants derived from them to
represent character classes. Learning in a nearest
neighbor classifier (type-A) is performed using ideal
images of characters and their variants. Pixel intensity
values are used as features. To judge on the effectiveness
of this classifier, another novel nearest neighbor classifier
(type-B) is built and trained using real images.
These classifiers are tested using a real dataset. The
overall recognition, error, and rejection rates of a threevariants
type-A classifier are 98.5%, 1.5%, and 0.0%,
respectively. The recognition rate of the type-B classifier
exceeds that of type-A classifier that uses three variants
by only 1.2%. Using other kinds of classifiers and using
multiple classifier technology is expected to produce
much impressive results for the type-A classifier. The
type-A classifier that uses three variants requires 57 ms
to recognize a character. The type-B classifier requires
less than one half of the time required by type-A
classifier.
|
| Keywords: | Ideal Images, Synthetic Datasets, Real
Datasets, Document Image Defect Models, Nearest
Neighbour Classifier.
|
| Journal/Conference: | ICGST Conference on Graphics, Vision and Image Processing, GVIP-05
|
| Volume: |
|
| Issue: |
|
| Submission Date: | 8/1/2005 12:00:00 AM
|
| Review Date: | 10/1/2005 12:00:00 AM
|
| Publishing Date: | 12/19/2005 12:00:00 AM
|
| Article Downloads: | 396
|
| Download: |
|