Text/Non-text Ink Stroke Classification in Japanese Handwriting Based on Markov Random Fields

Zhou, Xiangdong; Liu, Cheng‐Lin

doi:10.1109/icdar.2007.4378735

Cited by 35 publications

(14 citation statements)

References 12 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Jain et al [3] have proposed a classification system based on local features extracted from each stroke and a linear classifier. More recently, more sophisticated approaches have been proposed, taking into account the temporal context of the strokes [4], [5], [6], [7], the spatial context [8], or a combination of those [9]. In our recent work [10], we introduced a Conditional Random Field model that integrates multiple sources of context and yields a recognition rate of 97.23% on the IAM-OnDo documents [10].…”

Section: A Text/non-text Separationmentioning

confidence: 98%

Graphics Extraction from Heterogeneous Online Documents with Hierarchical Random Fields

Delaye

Liu

2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Graphical objects are important elements of freely handwritten notes but their segmentation from the document is challenging due to their irregular properties. This paper introduces an original solution for automatically segmenting diagrams and drawings from unstructured online documents. We propose a multi-scale representation of the document modeled as a hierarchical Conditional Random Field to predict the detection of graphical elements at the stroke level. An experimental evaluation with realistic documents highlights the benefit of the hierarchical model in comparison with a flat Conditional Random Field and demonstrates the robustness of our system.

show abstract

Section: A Text/non-text Separationmentioning

confidence: 98%

Graphics Extraction from Heterogeneous Online Documents with Hierarchical Random Fields

Delaye

Liu

2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

show abstract

“…MRFs can effectively integrate the information between neighboring pen-points such as binary features and triple features [3] and they have been successfully applied to offline handwritten character recognition [4] and on-line stroke classification [5]. However, MRFs have not been applied to on-line handwritten character recognition; current on-line handwritten character recognition tend to use HMM-based models (note that HMMs can be viewed as a specific case of MRFs).…”

Section: Introductionmentioning

confidence: 99%

On-line Handwritten Japanese Characters Recognition Using a MRF Model with Parameter Optimization by CRF

Zhu

Nakagawa

2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

This paper describes a Markov random field (MRF) model with weighting parameters optimized by conditional random field (CRF) for on-line recognition of handwritten Japanese characters. It also presents updated evaluation using a large testing set. The model extracts feature points along the pen-tip trace from pen-down to pen-up and sets each feature point from an input pattern as a site and each state from a character class as a label. It employs the coordinates of feature points as unary features and the differences in coordinates between the neighboring feature points as binary features. The weighting parameters are estimated by CRF or the minimum classification error (MCE) method. In experiments using the TUAT Kuchibue database, the method achieved a character recognition rate of 92.77%, which is higher than the previous model's rate, and the method of estimating the weighting parameters using CRF was more accurate than using MCE.

show abstract

“…The system matches feature points from the input pattern to each prototype of each character class based on the dynamic programming algorithm. It does not consider the distributions for each feature point and only uses the unary features to calculate the distances between matched pairs of feature points of the input pattern and each prototype, and then sum those distances to evaluate the similarity between the input pattern The MRF is described by an undirected graph in which a set of random variables have Markov property and, MRFs can effectively integrate the information among neighboring feature points such as binary features and trinary features [18] and they have been successfully applied to off-line handwritten character recognition [19] and on-line stroke classification [20]. Wolf, C. [21] has successfully employed MRF for document images binarization.…”

Section: Introductionmentioning

confidence: 99%

Online Handwritten Lao Character Recognition by MRF

Saysourinhong

Zhu

Nakagawa

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper describes on-line recognition of handwritten Lao characters by adopting Markov random field (MRF). The character set to recognize includes consonants, vowels and tone marks, 52 characters in total. It extracts feature points along the pen-tip trace from pen-down to pen-up, and then sets each feature point from an input pattern as a site and each state from a character class as a label. It recognizes an input pattern by using a linear-chain MRF model to assign labels to the sites of the input pattern. It employs the coordinates of feature points as unary features and the transitions of the coordinates between the neighboring feature points as binary features. An evaluation on the Lao character pattern database demonstrates the robustness of our proposed method with recognition rate of 92.41% and respectable recognition time of less than a second per character. key words: online handwritten character recognition, Lao character recognition, Markov random field

show abstract

Text/Non-text Ink Stroke Classification in Japanese Handwriting Based on Markov Random Fields

Abstract: Abstract

Cited by 35 publications

References 12 publications

Graphics Extraction from Heterogeneous Online Documents with Hierarchical Random Fields

Graphics Extraction from Heterogeneous Online Documents with Hierarchical Random Fields

On-line Handwritten Japanese Characters Recognition Using a MRF Model with Parameter Optimization by CRF

Online Handwritten Lao Character Recognition by MRF

Contact Info

Product

Resources

About