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
  • [1] An end-to-end network for irregular printed Mongolian recognition
    Cui, ShaoDong
    Su, YiLa
    Ji, Ren Qing dao er
    Ji, YaTu
    INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2022, 25 (01) : 41 - 50
  • [2] An end-to-end network for irregular printed Mongolian recognition
    ShaoDong Cui
    YiLa Su
    Ren Qing dao er ji
    YaTu Ji
    International Journal on Document Analysis and Recognition (IJDAR), 2022, 25 : 41 - 50
  • [3] An end-to-end administrative document analysis system
    Hamza, Hatem
    Belaid, Yolande
    Belaid, Abdel
    Chaudhuri, Bidyut B.
    PROCEEDINGS OF THE 8TH IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS, 2008, : 175 - 182
  • [4] End-to-end Piece-wise Unwarping of Document Images
    Das, Sagnik
    Singh, Kunwar Yashraj
    Wu, Jon
    Bas, Erhan
    Mahadevan, Vijay
    Bhotika, Rahul
    Samaras, Dimitris
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 4248 - 4257
  • [5] END-TO-END TRAINING OF A LARGE VOCABULARY END-TO-END SPEECH RECOGNITION SYSTEM
    Kim, Chanwoo
    Kim, Sungsoo
    Kim, Kwangyoun
    Kumar, Mehul
    Kim, Jiyeon
    Lee, Kyungmin
    Han, Changwoo
    Garg, Abhinav
    Kim, Eunhyang
    Shin, Minkyoo
    Singh, Shatrughan
    Heck, Larry
    Gowda, Dhananjaya
    2019 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU 2019), 2019, : 562 - 569
  • [6] What is that Building? An End-to-end System for Building Recognition from Streetside Images
    Zhang, Chiqun
    Yankov, Dragomir
    Wu, Chun-Ting
    Shapiro, Simon
    Hong, Jason
    Wu, Wei
    KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, : 2425 - 2433
  • [7] A Historical Document Handwriting Transcription End-to-end System
    Romero, Veronica
    Bosch, Vicente
    Hernandez, Celio
    Vidal, Enrique
    Andreu Sanchez, Joan
    PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2017), 2017, 10255 : 149 - 157
  • [8] Are End-to-End Systems Really Necessary for NER on Handwritten Document Images?
    Tueselmann, Oliver
    Wolf, Fabian
    Fink, Gernot A.
    DOCUMENT ANALYSIS AND RECOGNITION - ICDAR 2021, PT II, 2021, 12822 : 808 - 822
  • [9] An end-to-end framework for the detection of mathematical expressions in scientific document images
    Phong, Bui Hai
    Hoang, Thang Manh
    Le, Thi-Lan
    EXPERT SYSTEMS, 2022, 39 (01)
  • [10] End-to-end Billet Identification Number Recognition System
    Koo, Gyogwon
    Yun, Jong Pil
    Lee, Sang Jun
    Choi, Hyeyeon
    Kim, Sang Woo
    ISIJ INTERNATIONAL, 2019, 59 (01) : 98 - 103
12345