Script identification in handwritten and printed documents using convolutional recurrent connection

被引:0
|
作者
Jindal A. [1 ]
机构
[1] School of Computer Science, UPES, Bidholi, Uttarakhand, Dehradun
关键词
Bayesian optimization; CNN-LSTM; Deep learning; Script identification;
D O I
10.1007/s11042-024-19106-x
中图分类号
学科分类号
摘要
Identification of the script in multi-script handwritten or printed documents is one of the essential component to recognize the text. The script identification module helps Optical Character Recognition (OCR) to digitize the text present in the multi-script handwritten or printed documents. The similarity of characters between two or more scripts create this task tedious. The factors such as noise and writing style creates identification of the script more tedious. The present research work has proposed a deep learning method having a set of optimized convolutional layers followed by recurrently connected layers to identify the script of any word sample present in the handwritten or printed document. The proposed method has two components to extract deep hierarchical features and identify the temporal features. The experiments have been carried out on MDIW-13 and PHDIndic_11 datasets having handwritten and printed documents. The experimental results from the proposed method has improved the performance over existing methods in this regard. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
引用
收藏
页码:5549 / 5563
页数:14
相关论文
共 50 条
  • [21] Word-level Script Identification for Handwritten Indic scripts
    Singh, Pawan Kumar
    Sarkar, Ram
    Nasipuri, Mita
    Doermann, David
    2015 13TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2015, : 1106 - 1110
  • [22] Line-Level Script Identification for Six Handwritten Scripts Using Texture Based Features
    Singh, Pawan Kumar
    Sarkar, Ram
    Nasipuri, Mita
    INFORMATION SYSTEMS DESIGN AND INTELLIGENT APPLICATIONS, VOL 2, 2015, 340 : 285 - 293
  • [23] Quantum Particle Swarm Optimization Based Convolutional Neural Network for Handwritten Script Recognition
    Sharma, Reya
    Kaushik, Baijnath
    Gondhi, Naveen Kumar
    Tahir, Muhammad
    Rahmani, Mohammad Khalid Imam
    CMC-COMPUTERS MATERIALS & CONTINUA, 2022, 71 (03): : 5855 - 5873
  • [24] Neural network based system for script identification in Indian documents
    S. Basavaraj Patil
    N. V. Subbareddy
    Sadhana, 2002, 27 : 83 - 97
  • [25] Word Level Script Identification Using Convolutional Neural Network Enhancement for Scenic Images
    Mahajan, Shilpa
    Rani, Rajneesh
    ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2022, 21 (04)
  • [26] A Fuzzy Matching based Image Classification System for Printed and Handwritten Text Documents
    Puri, Shalini
    Singh, Satya Prakash
    JOURNAL OF INFORMATION TECHNOLOGY RESEARCH, 2020, 13 (02) : 155 - 194
  • [27] Neural network based system for script identification in Indian documents
    Patil, SB
    Subbareddy, NV
    SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, 2002, 27 (1): : 83 - 97
  • [28] Word-wise script identification from Indian documents
    Sinha, S
    Pal, U
    Chaudhuri, BB
    DOCUMENT ANALYSIS SYSTEMS VI, PROCEEDINGS, 2004, 3163 : 310 - 321
  • [29] Writer Identification in Historical Handwritten Documents: A Latin Dataset and a Benchmark
    Fagioli, Alessio
    Avola, Danilo
    Cinque, Luigi
    Colombi, Emanuela
    Foresti, Gian Luca
    IMAGE ANALYSIS AND PROCESSING - ICIAP 2023 WORKSHOPS, PT II, 2024, 14366 : 465 - 476
  • [30] Script identification in the wild via discriminative convolutional neural network
    Shi, Baoguang
    Bai, Xiang
    Yao, Cong
    PATTERN RECOGNITION, 2016, 52 : 448 - 458