Text Input System Using Online Overlapped Handwriting Recognition for Mobile Devices

Tonouchi, Yojiro; Kawamura, Akinori

doi:10.1109/icdar.2007.4377016

Cited by 5 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(7), the segmentation measure (F) defined in Eq. (8), which combines recall and precision rates, and the average recognition time cost per character pattern (T av rec c ).…”

Section: Results Of Experimentsmentioning

confidence: 99%

“…Using a bigram model consisting of 1,016 Japanese educational Kanji and 71 Hiragana characters, the character recognition rates are 74.9% for free stroke order patterns and 91.1% for fixed stroke order patterns. Tonouchi et al [8] proposed an on-line overlaid handwriting recognition system based on stroke-level discrete Markov Models to recognize 81 hiragana characters and 5 symbols. The recognized hiragana characters can be easily translated into kanji characters by gestures.…”

Section: Copyright Cmentioning

confidence: 99%

See 1 more Smart Citation

Character-Position-Free On-Line Handwritten Japanese Text Recognition by Two Segmentation Methods

Liang

Zhu

Kumagai

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARY The paper presents a recognition method of characterposition-free on-line handwritten Japanese text patterns to allow a user to overlay characters freely without confirming previously written characters. To develop this method, we first collected text patterns written without wrist or elbow support and without visual feedback and then prepared large sets of character-position-free handwritten Japanese text patterns artificially from normally handwritten text patterns. The proposed method sets each off-stroke between real strokes as undecided and evaluates the segmentation probability by SVM model. Then, the optimal segmentationrecognition path can be effectively found by Viterbi search in the candidate lattice, combining the scores of character recognition, geometric features, linguistic context, as well as the segmentation scores by SVM classification. We test this method on variously overlaid sample patterns, as well as on the above-mentioned collected handwritten patterns, and verify that its recognition rates match those of the latest recognizer for normally handwritten horizontal Japanese text with no serious speed restriction in practical applications.

show abstract

“…(7), the segmentation measure (F) defined in Eq. (8), which combines recall and precision rates, and the average recognition time cost per character pattern (T av rec c ).…”

Section: Results Of Experimentsmentioning

confidence: 99%

Section: Copyright Cmentioning

confidence: 99%

Character-Position-Free On-Line Handwritten Japanese Text Recognition by Two Segmentation Methods

Liang

Zhu

Kumagai

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…It can recognize 1016 Japanese educational Kanji and 71 Hiragana characters, and the recognition rate is about 69.2% when different stroke order was permitted. In [6], Tonouchi et al proposed a system to recognize overlapped handwritten Hiragana characters and convert those Hiragana characters to Kanji characters with special designed gestures. It shows that the efficiency of the proposed system is not lower than the efficiency of systems based on Multi-tap KKC method or multi-box handwriting input method.…”

Section: Introductionmentioning

confidence: 99%

Overlapped Handwriting Input on Mobile Phones

Zou

Liu

et al. 2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

In this paper, we propose an overlapped handwriting input method on handheld devices, which allows users to write continuously without breaks on a single size-restricted writing area. 2 issues have been considered during the implementation of the overlapped input method: previous characters on the background may obstruct the clear viewing of current character and the messy overlapped handwriting is difficult to be segmented and recognized. In our method, a quick segmentation method based on an artificial neural network is used to tackle the first problem and a novel system is implemented to recognize the messy handwriting based on the output of an isolated character recognition engine and a language model. The recognition rate for Chinese characters is about 92.5% for a testing database containing GB2312 Chinese characters and other frequently used symbols. The positive feedbacks from testers have also confirmed the validity of the proposed method.

show abstract

An online overlaid handwritten Japanese text recognition system for small tablet

Liang

Nguyen

Zhu

et al. 2018

Pattern Anal Applic

View full text Add to dashboard Cite

Text Input System Using Online Overlapped Handwriting Recognition for Mobile Devices

Cited by 5 publications

References 4 publications

Character-Position-Free On-Line Handwritten Japanese Text Recognition by Two Segmentation Methods

Character-Position-Free On-Line Handwritten Japanese Text Recognition by Two Segmentation Methods

Overlapped Handwriting Input on Mobile Phones

An online overlaid handwritten Japanese text recognition system for small tablet

Contact Info

Product

Resources

About