A Research on Handwritten Text Recognition

Abstract

Over the years we have started accumulating handwritten documents, like pdfs, doc files and numerous other formats for reading, writing and studying. Often we come across situations where we need to utilize the text of those documents. Manually transcribing large amounts of handwritten data is an arduous process that’s bound to be fraught with errors. Automated handwriting recognition can drastically cut down on the time required to transcribe large volumes of text, and also serve as a framework for developing future applications of machine learning. Recognition can be offline or online and both can be implemented in applications to progressively learn based on the user’s feedback while performing offline learning on data in parallel. Some recognition systems identify strokes, others apply recognition on a single character or entire words. Some steps involved in the area(in no particular order): Image preprocessing, Segmentation, Classification & Recognition, Feature Extraction. Finally, some limitations of the direction of current and future research are presented. Keywords: CNN, DTCN, TrOCR, DTCN, RNN