Online Handwritten Japanese Character String Recognition Incorporating Geometric Context

Zhou, Xiangdong; Yu, Jinlun; Liu, Cheng‐Lin; Nagasaki, Takeshi; Marukawa, Katsumi

doi:10.1109/icdar.2007.4378673

Cited by 48 publications

(21 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The likelihood, depending on the number of segmented characters, tends to recognize two or more characters as one character because a longer character sequence tends to have smaller evaluation score than a shorter one [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A robust model for on-line handwritten Japanese text recognition

et al. 2009

View full text Add to dashboard Cite

This paper describes a robust model for on-line handwritten Japanese text recognition. The method evaluates the likelihood of candidate segmentation paths by combining scores of character pattern size, inner gap, character recognition, single-character position, pair-character position, likelihood of candidate segmentation point and linguistic context. The path score is insensitive to the number of candidate patterns and the optimal path can be found by the Viterbi search. In experiments of handwritten Japanese sentence recognition, the proposed method yielded superior performance.

show abstract

Section: Introductionmentioning

confidence: 99%

“…To improve the segmentation and recognition accuracy, the string recognition process should consider character recognition, geometric features and linguistic context for segmentation path evaluation [1] [2].…”

Section: Introductionmentioning

confidence: 99%

A robust model for on-line handwritten Japanese text recognition

et al. 2009

View full text Add to dashboard Cite

show abstract

“…Handwritten sentence (character string) recognition is a difficult contextual classification problem involving character segmentation and recognition, and has been attacked by many researchers [1][2][3][4][5][6]. A feasible approach is the oversegmentation-based recognition fusing character recognition scores, linguistic context and geometric context [5,6].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Text Line Segmentation for Real-Time Recognition of Chinese Handwritten Sentences

Wang

Liu

2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Real-time recognition of handwritten sentences enables fast text input but the dynamic nature of writing makes reliable text line segmentation difficult. This paper proposes a method for real-time dynamic text line segmentation of online Chinese handwriting. The core of the method is a statistical classifier for modeling the geometric relationship between an ongoing stroke and the previous text lines, to assign the stroke into a previous line or form a new line. The method can deal with delayed strokes and therefore enables robust real-time recognition. We evaluated the segmentation performance on a dataset of online Chinese handwriting by simulating the real-time writing and recognition process. The experimental results demonstrate the effectiveness and robustness of the proposed method.

show abstract

“…Geometric context has been used in handwriting recognition to reduce character segmentation and recognition errors, by using various geometric features (such as character size, inter-character and betweencharacter gaps) and statistical models (geometric class means, Gaussian density models, discriminative classifiers, etc.) for handwritten word and Japanese character string recognition [9][10][11][12][13]. These methods cannot be used straightforwardly for Chinese handwriting due to its greater challenge.…”

Section: Introductionmentioning

confidence: 99%