A deep learning model for Ottoman OCR

被引:5
作者
Dolek, Ishak [1 ]
Kurt, Atakan [1 ]
机构
[1] Istanbul Univ Cerrahpasa, Engn Sch, Comp Engn Dept, Istanbul, Turkey
关键词
CNN; CTC; deep neural networks; LSTM; OCR; Ottoman; printed naksh font; RNN; NEURAL-NETWORK; RECOGNITION; SEGMENTATION; RETRIEVAL;
D O I
10.1002/cpe.6937
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
The Ottoman OCR is an open problem because the OCR models for Arabic do not perform well on Ottoman. The models specifically trained with Ottoman documents have not produced satisfactory results either. We present a deep learning model and an OCR tool using that model for the OCR of printed Ottoman documents in the naksh font. We propose an end-to-end trainable CRNN architecture consisting of CNN, RNN (LSTM), and CTC layers for the Ottoman OCR problem. An experimental comparison of this model, called , with the Tesseract Arabic, the Tesseract Persian, Abby Finereader, Miletos, and Google Docs OCR tools or models was performed using a test data set of 21 pages of original documents. With 88.86% raw text, 96.12% normalized text, and 97.37% joined text character recognition accuracy, the Hybrid model outperforms the others with a marked difference. Our model outperforms the next best model by a clear margin of 4% which is a significant improvement considering the difficulty of the Ottoman OCR problem, and the huge size of the Ottoman archives to be processed. The hybrid model also achieves 58% word recognition accuracy on normalized text which is the only rate above 50%.
引用
收藏
页数:17
相关论文
共 50 条
  • [41] Deep Learning Methods for Heart Sounds Classification: A Systematic Review
    Chen, Wei
    Sun, Qiang
    Chen, Xiaomin
    Xie, Gangcai
    Wu, Huiqun
    Xu, Chen
    ENTROPY, 2021, 23 (06)
  • [42] A Hybrid Deep Learning Model with Evolutionary Algorithm for Short-Term Load Forecasting
    Al Mamun, Abdullah
    Hoq, Muntasir
    Hossain, Eklas
    Bayindir, Ramazan
    2019 8TH INTERNATIONAL CONFERENCE ON RENEWABLE ENERGY RESEARCH AND APPLICATIONS (ICRERA 2019), 2019, : 886 - 891
  • [43] Ensemble deep learning model for optical character recognition
    Ashish Shetty
    Sanjeev Sharma
    Multimedia Tools and Applications, 2024, 83 : 11411 - 11431
  • [44] Ensemble deep learning model for optical character recognition
    Shetty, Ashish
    Sharma, Sanjeev
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (04) : 11411 - 11431
  • [45] A Novel Hybrid Deep Learning Model for Sentiment Classification
    Salur, Mehmet Umut
    Aydin, Ilhan
    IEEE ACCESS, 2020, 8 (58080-58093) : 58080 - 58093
  • [46] Chicken pox prediction using deep learning model
    Lee M.
    Kim J.W.
    Jang B.
    Jang, Beakcheol (bjang@smu.ac.kr), 2020, Korean Institute of Electrical Engineers (69) : 127 - 137
  • [47] Learning a Deep Motion Planning Model for Autonomous Driving
    Song, Sheng
    Hu, Xuemin
    Yu, Jin
    Bai, Liyun
    Chen, Long
    2018 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2018, : 1137 - 1142
  • [48] Deep Learning based, a New Model for Video Captioning
    Ozer, Elif Gusta
    Karapinar, Ilteber Nur
    Busbug, Sena
    Turan, Sumeyye
    Utku, Anil
    Akcayol, M. Ali
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2020, 11 (03) : 514 - 519
  • [49] Deep multiscale model learning
    Wang, Yating
    Cheung, Siu Wun
    Chung, Eric T.
    Efendiev, Yalchin
    Wang, Min
    JOURNAL OF COMPUTATIONAL PHYSICS, 2020, 406
  • [50] Deep neural combinational model (DNCM): digital image descriptor for child’s independent learning
    Nuzhat Naqvi
    M. Shujah Islam
    Mansoor Iqbal
    Shamsa Kanwal
    Asad Khan
    ZhongFu Ye
    Multimedia Tools and Applications, 2022, 81 : 29955 - 29975