Hidden Markov Models for Off-Line Cursive Handwriting Recognition
Andreas Fischer, Volkmar Frinken and Horst Bunke, University of Bern, Institute of Computer Science and Applied Mathematics, Neubrückstrasse 10, 3012 Bern, Switzerland, afischer@iam.unibe.ch
Abstract
Hidden Markov models nowadays belong to the most widely used statistical models for the challenging task of handwriting recognition in document images. In this chapter, we describe the predominant application given by segmentation-free recognition of handwritten text lines in presence of large vocabularies and multiple writers. A review of the state of the art is provided for feature sequence extraction, character appearance modeling, and language modeling. In particular, ...
Get Handbook of Statistics now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
