Objective Function Design for MCE-Based Combination of On-line and Off-line Character Recognizers for On-line Handwritten Japanese Text Recognition

Zhu, Bilan; Gao, Jinfeng; Nakagawa, Masaki

doi:10.1109/icdar.2011.125

Cited by 27 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is computationally expensive since the neighborhood relationships must be examined in two dimensions. Although the method introducing temporal information is very sensitive to stroke order variations, it is efficient in recognition speed, and combining it with an un-structural method can deal with the strokeorder variations [27,28]. Even for the one-dimensional neighborhood relationships applying MRFs instead of HMMs to integrate the information of binary features between the successively adjacent feature vectors in writing or position order can improve performance.…”

Section: Site: Feature Points From An Input Pattern S={s1 S2 S3…s12}mentioning

confidence: 99%

See 1 more Smart Citation

Online Handwritten Chinese/Japanese Character Recognition

Zhu¹,

Nakagawa²

2012

Advances in Character Recognition

Self Cite

View full text Add to dashboard Cite

Section: Site: Feature Points From An Input Pattern S={s1 S2 S3…s12}mentioning

confidence: 99%

“…In contrast, un-structural methods are robust against noises but very weak against character shape variations. By combining a structural method (structural recognizer) with an un-structural method (un-structural recognizer), the recognition accuracy improves since they compensate for their respective disadvantages [27,28].…”

Section: Introductionmentioning

confidence: 99%

Online Handwritten Chinese/Japanese Character Recognition

Zhu¹,

Nakagawa²

2012

Advances in Character Recognition

Self Cite

View full text Add to dashboard Cite

“…Employing the combination of on-line and off-line recognition methods for character recognition [12], each candidate character pattern is associated with a number of candidate classes with confidence scores. All the possible segmentations and recognition candidate classes are represented by a src-lattice as shown in Fig.…”

Section: Candidate Lattice Constructionmentioning

confidence: 99%

Semi-Incremental Recognition of On-Line Handwritten Japanese Text

Nguyen

Zhu

Nakagawa

2016

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARY This paper presents a semi-incremental recognition method for on-line handwritten Japanese text and its evaluation. As text becomes longer, recognition time and waiting time become large if it is recognized after it is written (batch recognition). Thus, incremental methods have been proposed with recognition triggered by every stroke but the recognition rates are damaged and more CPU time is incurred. We propose semi-incremental recognition and employ a local processing strategy by focusing on a recent sequence of strokes defined as "scope" rather than every new stroke. For the latest scope, we build and update a segmentation and recognition candidate lattice and advance the best-path search incrementally. We utilize the result of the best-path search in the previous scope to exclude unnecessary segmentation candidates. This reduces the number of candidate character recognition with the result of reduced processing time. We also reuse the segmentation and recognition candidate lattice in the previous scope for the latest scope. Moreover, triggering recognition processes every several strokes saves CPU time. Experiments made on TUAT-Kondate database show the effectiveness of the proposed semi-incremental recognition method not only in reduced processing time and waiting time, but also in recognition accuracy.

show abstract

“…A combined classifier of the two above is formed by a sum rule in which the total score of a combined classifier is derived by adding two classifiers. Their weighting parameters have been optimized by the minimum classification error (MCE) criterion [34].…”

Section: Similarity Measurementioning

confidence: 99%

Digital Ink Search Based on Character-Recognition Candidates Compared with Feature-Matching-Based Approach

Cheng

Zhu

Nakagawa

2013

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYThis paper presents an approach based on character recognition to searching for keywords in on-line handwritten Japanese text. It employs an on-line character classifier and an off-line classifier or a combined classifier, which produce recognition candidates, and it searches for keywords in the lattice of candidates. It integrates scores to individually recognize characters and their geometric context. We use quadratic discriminant function(QDF) or support vector machines(SVM) models to evaluate the geometric features of individual characters and the relationships between characters. This paper also presents an approach based on feature matching that employs on-line or off-line features. We evaluate three recognition-based methods, two feature-matching-based methods, as well as ideal cases of the latter and concluded that the approach based on character recognition outperformed that based on feature matching.

show abstract

Objective Function Design for MCE-Based Combination of On-line and Off-line Character Recognizers for On-line Handwritten Japanese Text Recognition

Cited by 27 publications

References 13 publications

Online Handwritten Chinese/Japanese Character Recognition

Online Handwritten Chinese/Japanese Character Recognition

Semi-Incremental Recognition of On-Line Handwritten Japanese Text

Digital Ink Search Based on Character-Recognition Candidates Compared with Feature-Matching-Based Approach

Contact Info

Product

Resources

About