TextCaps : Handwritten Character Recognition with Very Small Datasets

被引:44
作者
Jayasundara, Vinoj [1 ]
Jayasekara, Sandaru [1 ]
Jayasekara, Hirunima [1 ]
Rajasegaran, Jathushan [1 ]
Seneviratne, Suranga [2 ]
Rodrigo, Ranga [1 ]
机构
[1] Univ Moratuwa, Moratuwa, Sri Lanka
[2] Univ Sydney, Sydney, NSW, Australia
来源
2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV) | 2019年
关键词
D O I
10.1109/WACV.2019.00033
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Many localized languages struggle to reap the benefits of recent advancements in character recognition systems due to the lack of substantial amount of labeled training data. This is due to the difficulty in generating large amounts of labeled data for such languages and inability of deep learning techniques to properly learn from small number of training samples. We solve this problem by introducing a technique of generating new training samples from the existing samples, with realistic augmentations which reflect actual variations that are present in human hand writing, by adding random controlled noise to their corresponding instantiation parameters. Our results with a mere 200 training samples per class surpass existing character recognition results in the EMNIST-letter dataset while achieving the existing results in the three datasets: EMNIST-balanced, EMNIST-digits, and MNIST. We also develop a strategy to effectively use a combination of loss functions to improve reconstructions. Our system is useful in character recognition for localized languages that lack much labeled training data and even in other related more general contexts such as object recognition.
引用
收藏
页码:254 / 262
页数:9
相关论文
共 26 条
[1]  
[Anonymous], 2012, CoRR
[2]  
[Anonymous], 2017, COMMUN ACM, DOI DOI 10.1145/3065386
[3]  
[Anonymous], ICANN
[4]  
[Anonymous], CORR
[5]  
[Anonymous], 2017, CORR
[6]  
[Anonymous], 2017, CORR
[7]  
Bertinetto L., 2016, ADV NEURAL INFORM PR, P523, DOI DOI 10.48550/ARXIV.1606.05233
[8]  
Bhatnagar S., 2017, ICIIP, P1
[9]   Deep, Big, Simple Neural Nets for Handwritten Digit Recognition [J].
Ciresan, Dan Claudiu ;
Meier, Ueli ;
Gambardella, Luca Maria ;
Schmidhuber, Juergen .
NEURAL COMPUTATION, 2010, 22 (12) :3207-3220
[10]  
Cohen G., 2017, CORR