| Abstract: |  This work presents an algorithm for optical font recognition of a text in real-scene images. It is based on an OCR system TextSpotter developed at Czech Technical University in Prague. This system locates areas with a text, detects connected components of characters, binarizes them, extracts features and tries to recognize characters. The OCR system trains its classifier on all initial fonts. Some characters are not well recognized or they stay unrecognized because in some different fonts mismatching characters look similar. The goal of this project is to recognize a font of the text and to train the classifier only on this font. The unrecognized characters are then classified again by the classifier with a reduced training set. It is thus more likely that they will be classified correctly and the OCR quality increases.
|
|---|