Evaluation of Different Strategies to Optimize an HMM-Based Character Recognition System
2009Vol. 1, pp. 666–670
Murilo Santos, Albert H.R. Ko, Luis S. Oliveira, Robert Sabourin, Alessandro L. Koerich, Alceu S. Britto
Abstract
Different strategies for combination of complementary features in an HMM-based method for handwritten character recognition are evaluated. In addition, a noise reduction method is proposed to deal with the negative impact of low probability symbols in the training database. New sequences of observations are generated based on the original ones, but considering a noise reduction process. The experimental results based on 52 classes of alphabetic characters and more than 23,000 samples have shown that the strategies proposed to optimize the HMM-based recognition method are very promising.
Related Papers
- → A Method of Character Recognition Based on General Characteristic and Connected Regions(2011)3 cited
- → Character Recognition on Forged Entities using AI(2022)1 cited
- → Degraded character recognition based on gradient pattern(2010)4 cited
- → A Character Recognition Method for License Plate Based on Combination Feature and Partial Character Input(2018)