Artificial neural networks and fuzzy logic for recognizing alphabet characters and mathematical symbols
This work addresses the need for more accessible texts in OCR, particularly for handling mathematical symbols, though it appears incremental in its improvements to existing methods.
The authors tackled the problem of recognizing both normal texts and mathematical formulae in optical character recognition (OCR) by developing pattern recognition algorithms using artificial neural networks (ANN) and fuzzy logic, resulting in an improved backpropagation algorithm and a novel image segmentation method for separating touching characters.
Optical Character Recognition software (OCR) are important tools for obtaining accessible texts. We propose the use of artificial neural networks (ANN) in order to develop pattern recognition algorithms capable of recognizing both normal texts and formulae. We present an original improvement of the backpropagation algorithm. Moreover, we describe a novel image segmentation algorithm that exploits fuzzy logic for separating touching characters.