Experiment on Handwriting Generation with Recurrent Neural Networks using Small Datasets

被引：2

作者：

Liu, Yushun ^{[1
]}

Liu, Liguo ^{[2
]}

Miao, Xuhui ^{[3
]}

机构：

[1] Hong Kong Univ Sci & Technol, Dept Elect & Comp Engn, Hong Kong, Peoples R China

[2] Univ Missouri, Engn Dept, Columbia, MO 65211 USA

[3] Chatsworth, Sierra Canyon Sch, Bakewell, England

来源：

2021 5TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND VIRTUAL REALITY, AIVR 2021 | 2021年

关键词：

RNN; LSTM; Handwriting Generation; Handwriting Synthesis;

D O I：

10.1145/3480433.3480446

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper examines the performance of a specific Long-Short Term Memory Recurrent Neural Network for cursive handwriting generation when training with small datasets. The RNN can generate complex structure sequences by predicting one data point at a time. Then, by predicting the overall writing structure, the handwriting can be synthesized. The resulting network can generate different handwriting style parameters.

引用

页码：123 / 127

页数：5

共 50 条

[1] Online Japanese Handwriting Recognizers using Recurrent Neural Networks
Hung Tuan Nguyen
Cuong Tuan Nguyen
Nakagawa, Masaki
[J]. PROCEEDINGS 2018 16TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2018, : 435 - 440
[2] Synthesizing and Imitating Handwriting using Deep Recurrent Neural Networks and Mixture Density Networks
Kumar, K. Manoj
Kandala, Harish
Reddy, N. Sudhakar
[J]. 2018 9TH INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION AND NETWORKING TECHNOLOGIES (ICCCNT), 2018,
[3] Dropout improves Recurrent Neural Networks for Handwriting Recognition
Vu Pham
Bluche, Theodore
Kermorvant, Christopher
Louradour, Jerome
[J]. 2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2014, : 285 - 290
[4] Process modeling with neural networks using small experimental datasets
Lanouette, R
Thibault, J
Valade, JL
[J]. COMPUTERS & CHEMICAL ENGINEERING, 1999, 23 (09) : 1167 - 1176
[5] Handwriting Recognition by Attribute Embedding and Recurrent Neural Networks
Ignacio Toledo, J.
Dey, Sounak
Fornes, Alicia
Llados, Josep
[J]. 2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1, 2017, : 1038 - 1043
[6] Automatic playlist generation using Convolutional Neural Networks and Recurrent Neural Networks
Irene, Rosilde Tatiana
Borrelli, Clara
Zanoni, Massimiliano
Buccoli, Michele
Sarti, Augusto
[J]. 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2019,
[7] Arabic Text Generation Using Recurrent Neural Networks
Souri, Adnan
El Maazouzi, Zakaria
Al Achhab, Mohammed
Eddine El Mohajir, Badr
[J]. BIG DATA, CLOUD AND APPLICATIONS, BDCA 2018, 2018, 872 : 523 - 533
[8] Learning Generalizable Recurrent Neural Networks from Small Task-fMRI Datasets
Dvornek, Nicha C.
Yang, Daniel
Ventola, Pamela
Duncan, James S.
[J]. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, PT III, 2018, 11072 : 329 - 337
[9] Gated Convolutional Recurrent Neural Networks for Multilingual Handwriting Recognition
Bluche, Theodore
Messina, Ronaldo
[J]. 2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1, 2017, : 646 - 651
[10] Online Handwriting Mongolia Words Recognition with Recurrent Neural Networks
Wu Wei
Gao Guanglai
[J]. ICCIT: 2009 FOURTH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCES AND CONVERGENCE INFORMATION TECHNOLOGY, VOLS 1 AND 2, 2009, : 165 - 167

← 1 2 3 4 5 →