RNN Based Online Handwritten Word Recognition in Devanagari Script

被引:8
作者
Ghosh, Rajib [1 ]
Keshri, Pooja [1 ]
Kumar, Prabhat [1 ]
机构
[1] Natl Inst Technol Patna, Comp Sci & Engn Dept, Patna, Bihar, India
来源
PROCEEDINGS 2018 16TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR) | 2018年
关键词
Online handwriting; Word recognition; Devanagari script; Zone division; Recurrent neural network; LSTM; BLSTM;
D O I
10.1109/ICFHR-2018.2018.00096
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Devanagari script is the most popular script in India. But, very little recognized works have been done in this script towards development of online handwritten text recognition systems. The existence of large number of symbols and symbol order variations in this script, has led to low recognition rates for even the best existing recognition system. Most of the existing studies in Devanagari script have relied upon the same Hidden Markov Model (HMM) which has been used for so many years in handwriting recognition, despite of its familiar shortcomings. This article proposes a novel approach for online handwritten word recognition in Devanagari script based on two recently developed models of Recurrent Neural Network (RNN), termed as Long-Short Term Memory (LSTM) and Bidirectional Long-Short Term Memory (BLSTM), specifically designed for sequential data where the segmentation of data into basic unit level is very difficult. Analysis shows that words are written in non-cursive fashion in Devanagari script. The proposed approach considers the local zone wise analysis of each basic stroke of a word to extract various features from each basic stroke. In this local zone wise feature extraction approach, dominant points are detected from strokes using slope angles, to find the local features. These features are then studied using both LSTM and BLSTM versions of RNN. Most of the existing word recognition systems in this script have followed the typical holistic approach whereas the proposed system has been developed in analytical scheme with a total of 10K words in lexicon. An exhaustive experiment on large datasets has been performed to evaluate the performance of the proposed recognition approach using both LSTM and BLSTM to make a comparative performance analysis. Experimental results show that the proposed system outperforms existing HMM based systems in the literature.
引用
收藏
页码:517 / 522
页数:6
相关论文
共 50 条
[41]   Online Handwritten Mathematical Symbol Segmentation and Recognition with Bidirectional Context [J].
Cuong Tuan Nguyen ;
Thanh-Nghia Truong ;
Huy Quang Ung ;
Nakagawa, Masaki .
2020 17TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR 2020), 2020, :355-360
[42]   Handwritten Bangla word recognition using negative refraction based shape transformation [J].
Sahoo, Samanway ;
Nandi, Subham Kumar ;
Barua, Sourav ;
Pallavi ;
Bhowmik, Showmik ;
Malakar, Samir ;
Sarkar, Ram .
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2018, 35 (02) :1765-1777
[43]   Sub-word Based Offline Handwritten Farsi Word Recognition Using Recurrent Neural Network [J].
Ghadikolaie, Mohammad Fazel Younessy ;
Kabir, Ehsanolah ;
Razzazi, Farbod .
ETRI JOURNAL, 2016, 38 (04) :703-713
[44]   Hyper Parameter Optimization of CRNN for Printed Devanagari Script Recognition using Taguchi's Method [J].
Akhter, Shaheera Saba Mohd Naseem ;
Rege, Priti P. .
ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2023, 22 (04)
[45]   Digits Recognition of Marathi Handwritten Script using LSTM Neural Network [J].
Patil, Yamini ;
Bhilare, Amol .
2019 5TH INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION, CONTROL AND AUTOMATION (ICCUBEA), 2019,
[46]   Bagging: An Ensemble Approach for Recognition of Handwritten Place Names in Gurumukhi Script [J].
Kaur, Harmandeep ;
Kumar, Munish ;
Gupta, Aastha ;
Sachdeva, Monika ;
Mittal, Ajay ;
Kumar, Krishan .
ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2023, 22 (07)
[47]   Handwritten Digit String Recognition by Combination of Residual Network and RNN-CTC [J].
Zhan, Hongjian ;
Wang, Qingqing ;
Lu, Yue .
NEURAL INFORMATION PROCESSING (ICONIP 2017), PT VI, 2017, 10639 :583-591
[48]   Advances in online handwritten recognition in the last decades [J].
Ghosh, Trishita ;
Sen, Shibaprasad ;
Obaidullah, Sk. Md. ;
Santosh, K. C. ;
Roy, Kaushik ;
Pal, Umapada .
COMPUTER SCIENCE REVIEW, 2022, 46
[49]   A tree-BLSTM-based recognition system for online handwritten mathematical expressions [J].
Ting Zhang ;
Harold Mouchère ;
Christian Viard-Gaudin .
Neural Computing and Applications, 2020, 32 :4689-4708
[50]   A Segmentation-driven Handwritten Uighur Word Recognition Algorithm Based on Feedback Structure [J].
Xu, Yamei ;
Xue, Jili .
PROCEEDINGS OF 2019 IEEE 10TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND SERVICE SCIENCE (ICSESS 2019), 2019, :419-423