M
Masaki Nakagawa
Researcher at Tokyo University of Agriculture and Technology
Publications - 268
Citations - 3220
Masaki Nakagawa is an academic researcher from Tokyo University of Agriculture and Technology. The author has contributed to research in topics: Handwriting recognition & Intelligent word recognition. The author has an hindex of 26, co-authored 268 publications receiving 2900 citations. Previous affiliations of Masaki Nakagawa include University at Buffalo & University of Tokyo.
Papers
More filters
Proceedings ArticleDOI
On-line text/drawings segmentation of handwritten patterns
TL;DR: The authors propose online but delayed processing of handwritten patterns after they are written, and a simple and fast segmentation of text and line drawings which exploits the characteristics of online handwritten patterns is presented.
Proceedings ArticleDOI
Recognizing Unconstrained Vietnamese Handwriting By Attention Based Encoder Decoder Model
TL;DR: The experiential results show that the proposed AED model achieves 12.30% of word error rate without using language model, which is competitive with the handwriting recognition system provided by Google in the Vietnamese Online Handwritten Text Recognition competition.
Proceedings ArticleDOI
A MRF model with parameter optimization by CRF for on-line recognition of handwritten Japanese characters
Bilan Zhu,Masaki Nakagawa +1 more
TL;DR: A Markov random field model with weighting parameters optimized by conditional random field (CRF) for on-line recognition of handwritten Japanese characters achieves a character recognition rate higher than the previous model's rate and the method of estimating the weighting Parameters using CRF was more accurate than using MCE.
Proceedings ArticleDOI
ICFHR 2018 – Competition on Vietnamese Online Handwritten Text Recognition using HANDS-VNOnDB (VOHTR2018)
TL;DR: This paper presents the results of the VOHTR 2018 competition on Vietnamese Online Handwritten Text Recognition and describes the evaluation metrics and comparative results of competitors along with the brief descriptions of the respective methods.
Proceedings ArticleDOI
Prototype learning algorithms for nearest neighbor classifier with application to handwritten character recognition
Cheng-Lin Liu,Masaki Nakagawa +1 more
TL;DR: Experimental results of handwritten numeral recognition and Chinese character recognition show that the global optimization algorithms generally outperform LVQ.