Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

DeepDyve requires Javascript to function. Please enable Javascript on your browser to continue.

Chinese Handwriting Recognition: An Algorithmic Perspective

Part of the SpringerBriefs in Electrical and Computer Engineering Book Series

DOI: 10.1007/978-3-642-31812-2

ISBN: 978-3-642-31811-5

Publisher: Springer Berlin Heidelberg - Springer Journals

Jan 11, 2013

LitStream

Chapter 1Introduction

Su, Tonghua

Pages: 1 –21

[Chinese character recognition, as an attractive toolset for Chinese digital library projects, has been drawing intense attention. The Chinese character system is used for communication and has served various political purposes in China, having played an important role in the development of...
LitStream

Chapter 2HIT-MW Database

Su, Tonghua

Pages: 23 –48

[Standard databases play a fundamental part in handwriting recognition research. This chapter presents a Chinese handwriting database named HIT-MW, designed to facilitate Chinese handwritten text recognition. Both the writers and the texts for handcopying are carefully sampled using a systematic...
LitStream

Chapter 3Integrated Segmentation-Recognition Strategy

Su, Tonghua

Pages: 49 –78

[Reliable recognition of realistic Chinese handwriting is of overwhelming interest yet remains a challenging undertaking. Both sufficient training samples and advanced learning methods are critical to identifying the underlying symbols of a string image. This chapter first outlines two integrated...
LitStream

Chapter 4Segmentation-Free Strategy: Basic Algorithms

Su, Tonghua

Pages: 79 –97

[The off-line recognition of realistic Chinese handwriting poses significant challenges. This chapter presents a baseline system for a HMMs-based, segmentation-free strategy to address this problem, in which the character segmentation stage is avoided prior to recognition. Handwritten text lines...
LitStream

Chapter 5Segmentation-Free Strategy: Advanced Algorithms

Su, Tonghua

Pages: 99 –124

[The hidden Markov model (HMM), a powerful tool, has been widely applied to sequence analysis tasks such as speech recognition and handwriting recognition performance. However, its recognition performance is normally limited to the general framework. In this chapter, we investigate sophisticated...

results per page

Prev
1
Next

Browse All eBooks