End-to-end system for printed Amazigh script recognition in document images

被引：0
|
作者：
Aharrane, Nabil [1 ]
Dahmouni, Abdellatif [1 ]
Ensah, Karim El Moutaouakil [2 ]
Satori, Khalid [1 ]
机构：
[1] USMBA Univ, LIIAN Lab, Fes, Morocco
[2] Univ Mohammed 1, ENSAH, Al Hoceima, Morocco
来源：
2017 3RD INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES FOR SIGNAL AND IMAGE PROCESSING (ATSIP) | 2017年
关键词：
Amazigh OCR; language identification; deep learning; convolutionnal neural network; machine learning;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
in this work, we present an end-to-end system devoted to automatic recognition of printed Amazigh script in complex document images containing different languages such as Web images and natural scene images. To this end, text extraction from images is performed; the extracted text serves as input for a trained convolutional neural network (CNN) to identify its language. Finally, we proceed to the recognition of the Amazigh text script using a developed optical character recognition (OCR) system. The CNN reaches 99,12% of accuracy while the OCR system gets 99,93% The obtained results seem to be very satisfactory.
引用
收藏
页码：313 / 318
页数：6
相关论文
共 50 条
  • [41] End-to-end speech recognition system based on improved CLDNN structure
    Feng, Yujie
    Zhang, Yi
    Xu, Xuan
    PROCEEDINGS OF 2019 IEEE 8TH JOINT INTERNATIONAL INFORMATION TECHNOLOGY AND ARTIFICIAL INTELLIGENCE CONFERENCE (ITAIC 2019), 2019, : 538 - 542
  • [42] Transfer Learning Approaches for Streaming End-to-End Speech Recognition System
    Joshi, Vikas
    Zhao, Rui
    Mehta, Rupesh R.
    Kumar, Kshitiz
    Li, Jinyu
    INTERSPEECH 2020, 2020, : 2152 - 2156
  • [43] Local features-based script recognition from printed bilingual document images
    Abirami, S.
    Manjula, D.
    INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS IN TECHNOLOGY, 2010, 38 (04) : 283 - 297
  • [44] End-To-End Deep-Learning-Based Tamil Handwritten Document Recognition and Classification Model
    Vinotheni, C.
    Pandian, S. Lakshmana
    IEEE ACCESS, 2023, 11 : 43195 - 43204
  • [45] An End-to-End Security Approach for Digital Document Management
    Diego Munoz-Hernandez, Mario
    Morales-Sandoval, Miguel
    Juan Garcia-Hernandez, Jose
    COMPUTER JOURNAL, 2016, 59 (07): : 1076 - 1090
  • [46] End-to-End Unsupervised Document Image Blind Denoising
    Gangeh, Mehrdad J.
    Plata, Marcin
    Nezhad, Hamid R. Motahari
    Duffy, Nigel P.
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 7868 - 7877
  • [47] DocEnTr: An End-to-End Document Image Enhancement Transformer
    Souibgui, Mohamed Ali
    Biswas, Sanket
    Jemni, Sana Khamekhem
    Kessentini, Yousri
    Fornes, Alicia
    Llados, Josep
    Pal, Umapada
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 1699 - 1705
  • [48] An Open Architecture for End-to-End Document Analysis Benchmarking
    Lamiroy, Bart
    Lopresti, Daniel
    11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 42 - 47
  • [49] IMPROVING UNSUPERVISED STYLE TRANSFER IN END-TO-END SPEECH SYNTHESIS WITH END-TO-END SPEECH RECOGNITION
    Liu, Da-Rong
    Yang, Chi-Yu
    Wu, Szu-Lin
    Lee, Hung-Yi
    2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018), 2018, : 640 - 647
  • [50] END-TO-END VISUAL SPEECH RECOGNITION WITH LSTMS
    Petridis, Stavros
    Li, Zuwei
    Pantic, Maja
    2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 2592 - 2596
12345