A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks

被引：0
|
作者：
Liwicki, Marcus [1 ]
Graves, Alex [2 ]
Bunke, Horst [1 ]
Schmidhuber, Juergyen [2 ,3 ]
机构：
[1] Univ Bern, Inst Comp Sci & Appl Math, Neubruckstr 10, CH-3012 Bern, Switzerland
[2] IDSIA, Lugano, Switzerland
[3] Tech Univ Munich, D-85748 Garching, Germany
来源：
ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS | 2007年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper we introduce a new connectionist approach to on-line handwriting recognition and address in particular the problem of recognizing handwritten whiteboard notes. The approach uses a bidirectional recurrent neural network with the long short-term memory architecture. We use a recently introduced objective function, known as Connectionist Temporal Classification (CTC), that directly trains the network to label unsegmented sequence data. Our new system achieves a word recognition rate of 74.0% compared with 63.9 %, using a previously developed HMM-based recognition system.
引用
收藏
页码：367 / +
页数：2
相关论文
共 50 条
  • [1] Recognition of ships based on vector sensor and bidirectional long short-term memory networks
    Li, Sichun
    Yang, Shuyu
    Liang, Jinghan
    APPLIED ACOUSTICS, 2020, 164
  • [2] Handwriting Recognition with Large Multidimensional Long Short-Term Memory Recurrent Neural Networks
    Voigtlaender, Paul
    Doetsch, Patrick
    Ney, Hermann
    PROCEEDINGS OF 2016 15TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2016, : 228 - 233
  • [3] BIDIRECTIONAL QUATERNION LONG SHORT-TERM MEMORY RECURRENT NEURAL NETWORKS FOR SPEECH RECOGNITION
    Parcollet, Titouan
    Morchid, Mohamed
    Linares, Georges
    De Mori, Renato
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 8519 - 8523
  • [4] Combination of context-dependent bidirectional long short-term memory classifiers for robust offline handwriting recognition
    Chherawala, Youssouf
    Roy, Partha Pratim
    Cheriet, Mohamed
    PATTERN RECOGNITION LETTERS, 2017, 90 : 58 - 64
  • [5] A sentiment analysis method based on bidirectional long short-term memory networks
    Zhang, Haifei
    Xu, Jian
    Lei, Liting
    Qiu Jianlin
    Alshalabi, Riyad
    APPLIED MATHEMATICS AND NONLINEAR SCIENCES, 2023, 8 (01) : 55 - 68
  • [6] CCG supertagging with bidirectional long short-term memory networks
    Kadari, Rekia
    Zhang, Yu
    Zhang, Weinan
    Liu, Ting
    NATURAL LANGUAGE ENGINEERING, 2018, 24 (01) : 77 - 90
  • [7] Research on Chinese Irony Recognition by Integrating BERT and Bidirectional Long Short-Term Memory Networks
    Wang, Xuyang
    Qi, Nan
    Wei, Shenyou
    Computer Engineering and Applications, 2024, 60 (20) : 153 - 159
  • [8] Kannada Named Entity Recognition and Classification using Bidirectional Long Short-Term Memory Networks
    Sathyanarayanan, Dinesh
    Ashok, Ashwin
    Mishra, Debanik
    Chimalamarri, Santwana
    Sitaram, Dinkar
    2018 3RD INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONICS, COMMUNICATION, COMPUTER, AND OPTIMIZATION TECHNIQUES (ICEECCOT - 2018), 2018, : 65 - 71
  • [9] Bidirectional Long Short-Term Memory Network for Vehicle Behavior Recognition
    Zhu, Jiasong
    Sun, Ke
    Jia, Sen
    Lin, Weidong
    Hou, Xianxu
    Liu, Bozhi
    Qiu, Guoping
    REMOTE SENSING, 2018, 10 (06)
  • [10] Recognition of Dysfluency in Speech: A Bidirectional Long-Short Term Memory Based Approach
    Vinay, N. A.
    Bharathi, S. H.
    Aradhya, V. N. Manjunath
    APPLIED INTELLIGENCE AND INFORMATICS, AII 2021, 2021, 1435 : 232 - 244
12345