A new approach of feature extraction of printed Bengali characters
Alvi Mahadi, Munira Akter Lata, Mohammad Abu Yousuf · 2017
This work proposes a new method of feature extraction of printed Bengali alphabets that can be used for Optical Character Recognition or Classification. This work proposes some specific features and the method that can be used to detect and extract the features that can be used to effectively distinguish between two characters. This method also keeps in mind that the feature space for an alphabet do not get very bigger and so the way to real time recognition becomes much easier. A specific number system has been used to represent the presence or absence of each feature that can be used later in the recognition phase for grouping or classification.