Proceedings Article10.1109/ICDAR.2011.21
Transcript Mapping for Handwritten Text Lines Using Conditional Random Fields
Xiang-Dong Zhou,Fei Yin,Da-Han Wang,Qiu-Feng Wang,Masaki Nakagawa,Cheng-Lin Liu +5 more
- 18 Sep 2011
- pp 58-62
TL;DR: A conditional random field model for aligning online handwritten Chinese/Japanese text lines (character strings) with the corresponding transcripts and experimental results on two online databases demonstrate the effectiveness of the proposed method.
read more
Abstract: This paper presents a conditional random field (CRF) model for aligning online handwritten Chinese/Japanese text lines (character strings) with the corresponding transcripts. The CRF model is defined on a lattice which contains all possible segmentation hypotheses. The feature functions characterize the shape and context dependences of characters, including the scores of character recognition and the geometric compatibilities between characters. The combining parameters are optimized by energy minimization. Experimental results on two online databases: CASIA-OLHWDB and TUAT Kondate demonstrate the effectiveness of the proposed method.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Exploiting forced alignment of time-reversed data for improving HMM-based handwriting segmentation
TL;DR: An automatic boundary correction method is proposed which utilizes both the forward and the reverse direction alignments of handwritten data with its transcription which improves the alignment of data and thus the character boundaries in cursive handwriting.
10
Character N-Gram Spotting on Handwritten Documents Using Weakly-Supervised Segmentation
Udit Roy,Naveen Sankaran,K. Pramod Sankar,C. V. Jawahar +3 more
- 25 Aug 2013
TL;DR: This paper poses the problem of building a retrieval system over handwritten document images that is recognition-free, allows text-querying, can retrieve at sub-word level, and can search for out-of-vocabulary words as one of weakly-supervised learning.
References
•Proceedings Article
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
John Lafferty,Andrew McCallum,Fernando Pereira +2 more
- 28 Jun 2001
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
A Tutorial on Energy-Based Learning
Yann LeCun,Sumit Chopra,Raia Hadsell,Aurelio Ranzato,Fu Jie Huang +4 more
- 01 Jan 2006
TL;DR: The EBM approach provides a common theoretical framework for many learning models, including traditional discr iminative and generative approaches, as well as graph-transformer networks, co nditional random fields, maximum margin Markov networks, and several manifold learning methods.
CASIA Online and Offline Chinese Handwriting Databases
Cheng-Lin Liu,Fei Yin,Da-Han Wang,Qiu-Feng Wang +3 more
- 18 Sep 2011
TL;DR: A pair of online and offline Chinese handwriting databases, containing samples of isolated characters and handwritten texts, are introduced, which can be used for the research of various handwritten document analysis tasks.
•Book
Character Recognition Systems: A Guide for Students and Practitioners
Mohammed Cheriet,Nawwaf Kharma,Cheng-Lin Liu,Ching Y. Suen +3 more
- 12 Oct 2007
TL;DR: This chapter discusses the development of Character Recognition, Evolution and Development, and some of the techniques used to achieve this goal, including Bayes Decision Theory, as well as some new methods based onributed graph matching.
344