Neural Probabilistic System for Text Recognition
This work addresses the problem of recognizing text with unlimited vocabulary and varied styles for pattern recognition applications, but it appears incremental as it builds on existing methods like Sparse Auto-Encoders and Hidden Markov Models.
The authors tackled unconstrained text recognition by proposing a novel feature extraction model using a Bag of Features Framework based on Sparse Auto-Encoder, with Hidden Markov Models for sequence modeling, achieving promising recognition results on PKHATT and APTI datasets.
Unconstrained text recognition is a stimulating field in the branch of pattern recognition. This field is still an open search due to the unlimited vocabulary, multi styles, mixed-font and their great morphological variability. Recent trends show a potential improvement of recognition by adoption a novel representation of extracted features. In the present paper, we propose a novel feature extraction model by learning a Bag of Features Framework for text recognition based on Sparse Auto-Encoder. The Hidden Markov Models are then used for sequences modeling. For features learned quality evaluation, our proposed system was tested on two printed text datasets PKHATT text line images and APTI word images benchmark. Our method achieves promising recognition on both datasets.