Papers by Rohit Durvasula
Optical Character Recognition (OCR) is a very well-studied problem in the vast area of pattern re... more Optical Character Recognition (OCR) is a very well-studied problem in the vast area of pattern recognition. As the name suggests it involves recognising characters from a scanned image or from a photograph of a text. It has been around for many years and implemented in many applications ranging from Banking to Healthcare. Methods such as use of Artificial Neural Networks in order to train a program that can recognise a set of characters have become very famous. However not every time is such a complex method needed. For example in fixed-font character based recognition, when we know the topography (i.e. structure) of an alphabet beforehand , we can implement OCR by using some very simple feature extraction based algorithms that can determine the character with high degree of probability. This paper aims at evaluating the performance of a feature based extraction method for implementing OCR (only fixed-font).
Uploads
Papers by Rohit Durvasula