Machine Learning Approach for Arabic Handwritten Recognition

被引:0
|
作者
Mutawa, A. M. [1 ,2 ]
Allaho, Mohammad Y. [1 ]
Al-Hajeri, Monirah [1 ]
机构
[1] Kuwait Univ, Coll Engn & Petr, Dept Comp Engn, Safat 13060, Kuwait
[2] Univ Hamburg, Comp Sci Dept, D-22527 Hamburg, Germany
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 19期
关键词
machine learning; handwritten recognition systems; Arabic handwriting; BiLSTM; ResNet; natural language processing; NEURAL-NETWORK;
D O I
10.3390/app14199020
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Text recognition is an important area of the pattern recognition field. Natural language processing (NLP) and pattern recognition have been utilized efficiently in script recognition. Much research has been conducted on handwritten script recognition. However, the research on the Arabic language for handwritten text recognition received little attention compared with other languages. Therefore, it is crucial to develop a new model that can recognize Arabic handwritten text. Most of the existing models used to acknowledge Arabic text are based on traditional machine learning techniques. Therefore, we implemented a new model using deep machine learning techniques by integrating two deep neural networks. In the new model, the architecture of the Residual Network (ResNet) model is used to extract features from raw images. Then, the Bidirectional Long Short-Term Memory (BiLSTM) and connectionist temporal classification (CTC) are used for sequence modeling. Our system improved the recognition rate of Arabic handwritten text compared to other models of a similar type with a character error rate of 13.2% and word error rate of 27.31%. In conclusion, the domain of Arabic handwritten recognition is advancing swiftly with the use of sophisticated deep learning methods.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] Handwritten Arabic and Roman word recognition using holistic approach
    Malakar, Samir
    Sahoo, Samanway
    Chakraborty, Anuran
    Sarkar, Ram
    Nasipuri, Mita
    VISUAL COMPUTER, 2023, 39 (07): : 2909 - 2932
  • [22] A Novel Approach for the Recognition of a Wide Arabic Handwritten Word Lexicon
    Ben Cheikh, I.
    Belaid, A.
    Kacem, A.
    19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6, 2008, : 3055 - 3058
  • [23] Recognition of Handwritten Arabic Literal Amounts Using a Hybrid Approach
    Boukharouba, Abdelhak
    Bennia, Abdelhak
    COGNITIVE COMPUTATION, 2011, 3 (02) : 382 - 393
  • [24] Handwritten Arabic and Roman word recognition using holistic approach
    Samir Malakar
    Samanway Sahoo
    Anuran Chakraborty
    Ram Sarkar
    Mita Nasipuri
    The Visual Computer, 2023, 39 : 2909 - 2932
  • [25] Recognition of Handwritten Arabic Literal Amounts Using a Hybrid Approach
    Abdelhak Boukharouba
    Abdelhak Bennia
    Cognitive Computation, 2011, 3 : 382 - 393
  • [26] A Hybrid Approach for Deep Generative Handwritten Arabic Text Recognition
    Lamtougui, Hicham
    El Moubtahij, Hicham
    Fouadi, Hassan
    Satori, Khalid
    JOURNAL OF ADVANCES IN INFORMATION TECHNOLOGY, 2024, 15 (10) : 1138 - 1147
  • [27] Arabic/Latin and Handwritten/Machine-printed Formula Classification and Recognition
    Ayeb, Kawther Khazri
    Echi, Afef Kacem
    Belaid, Abdel
    2017 1ST INTERNATIONAL WORKSHOP ON ARABIC SCRIPT ANALYSIS AND RECOGNITION (ASAR), 2017, : 90 - 94
  • [28] Towards Unsupervised Learning for Arabic Handwritten Recognition Using Deep Architectures
    Elleuch, Mohamed
    Tagougui, Najiba
    Kherallah, Monji
    NEURAL INFORMATION PROCESSING, PT I, 2015, 9489 : 363 - 372
  • [29] Handwritten Arabic Numeral Recognition using Deep Learning Neural Networks
    Ashiquzzaman, Akm
    Tushar, Abdul Kawsar
    2017 IEEE INTERNATIONAL CONFERENCE ON IMAGING, VISION & PATTERN RECOGNITION (ICIVPR), 2017,
  • [30] Learning Vector Quantization algorithm as classifier for Arabic handwritten characters recognition
    Ali, Mohamed A.
    Bin Jumari, Kasmiran
    Samad, Salina Abd.
    PROCEEDINGS OF THE 6TH WSEAS INTERNATIONAL CONFERENCE ON APPLIED COMPUTER SCIENCE, 2007, : 240 - +