Improving CNN-RNN Hybrid Networks for Handwriting Recognition

被引:95
作者
Dutta, Kartik [1 ]
Krishnan, Praveen [1 ]
Mathew, Minesh [1 ]
Jawahar, C. V. [1 ]
机构
[1] IIIT Hyderabad, CVIT, Hyderabad, Telangana, India
来源
PROCEEDINGS 2018 16TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR) | 2018年
关键词
Handwriting recognition; CNN-RNN network; Data augmentation; Image pre-processing;
D O I
10.1109/ICFHR-2018.2018.00023
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The success of deep learning based models have centered around recent architectures and the availability of large scale annotated data. In this work, we explore these two factors systematically for improving handwritten recognition for scanned off-line document images. We propose a modified CNN-RNN hybrid architecture with a major focus on effective training using: (i) efficient initialization of network using synthetic data for pre-training, (ii) image normalization for slant correction and (iii) domain specific data transformation and distortion for learning important invariances. We perform a detailed ablation study to analyze the contribution of individual modules and present state of art results for the task of unconstrained line and word recognition on popular datasets such as IAM, RIMES and GW.
引用
收藏
页码:80 / 85
页数:6
相关论文
共 36 条
[21]  
Liu W., 2016, BRIT MACH VIS C BMVC, V2, P7
[22]   The IAM-database: An English sentence database for offline handwriting recognition [J].
U.-V. Marti ;
H. Bunke .
International Journal on Document Analysis and Recognition, 2002, 5 (1) :39-46
[23]   Quantitative Analysis of Culture Using Millions of Digitized Books [J].
Michel, Jean-Baptiste ;
Shen, Yuan Kui ;
Aiden, Aviva Presser ;
Veres, Adrian ;
Gray, Matthew K. ;
Pickett, Joseph P. ;
Hoiberg, Dale ;
Clancy, Dan ;
Norvig, Peter ;
Orwant, Jon ;
Pinker, Steven ;
Nowak, Martin A. ;
Aiden, Erez Lieberman .
SCIENCE, 2011, 331 (6014) :176-182
[24]   CNN-N-Gram for Handwriting Word Recognition [J].
Poznanski, Arik ;
Wolf, Lior .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2305-2314
[25]  
Puigcerver J., 2017, ICDAR
[26]  
Shi Baoguang, 2016, IEEE T PATTERN ANAL
[27]  
Simard PY, 2003, PROC INT CONF DOC, P958
[28]  
Stuner B., 2016, ABS161207528 CORR
[29]  
Sudholt S, 2016, INT CONF FRONT HAND, P277, DOI [10.1109/ICFHR.2016.0060, 10.1109/ICFHR.2016.55]
[30]   Offline continuous handwriting recognition using sequence to sequence neural networks [J].
Sueiras, Jorge ;
Ruiz, Victoria ;
Sanchez, Angel ;
Velez, Jose F. .
NEUROCOMPUTING, 2018, 289 :119-128