Sampling and quantization of bilevel signals
Pattern Recognition Letters
N-Tuple Features for OCR Revisited
IEEE Transactions on Pattern Analysis and Machine Intelligence
Large-Scale Simulation Studies in Image Pattern Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Spatial Sampling of Printed Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
Characterization of image degradation caused by scanning
Pattern Recognition Letters
Optical Font Recognition for Multi-Font OCR and Document Processing
DEXA '99 Proceedings of the 10th International Workshop on Database & Expert Systems Applications
Scanner Parameter Estimation Using Bilevel Scans of Star Charts
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Statistical image differences, degradation features, and character distance metrics
International Journal on Document Analysis and Recognition
Style Context with Second-Order Statistics
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
Printing and scanning of text documents introduces degradations to the characters which can be modeled. Interestingly, certain combinations of the parameters that govern the degradations introduced by the printing and scanning process affect characters in such a way that the degraded characters have a similar appearance, while other degradations leave the characters with an appearance that is very different. It is well known that (generally speaking) a test set that more closely matches a training set will be recognized with higher accuracy than one that matches the training set less well. Likewise, classifiers tend to perform better on data sets that have lower variance. This paper explores an analytical method that uses a formal printer/scanner degradation model to identify the similarity between groups of degraded characters. This similarity is shown to improve the recognition accuracy of a classifier through model directed choice of training set data.