A Novel Multi-head Attention and Long Short-Term Network for Enhanced Inpainting of Occluded Handwriting

In the domain of handwritten character recognition, inpainting occluded offline characters is essential. Relying on the remarkable achievements of transformers in various tasks, we present a novel framework called “Enhanced Inpainting with Multi-head Attention and stacked long short-term memory (LST...

Full description

Saved in:
Bibliographic Details
Published in:Cognitive computation 2025-02, Vol.17 (1), p.6, Article 6
Main Authors: Rabhi, Besma, Elbaati, Abdelkarim, Hamdi, Yahia, Dhahri, Habib, Pal, Umapada, Chabchoub, Habib, Ouahada, Khmaies, Alimi, Adel M.
Format: Article
Language:English
Subjects:
Artificial Intelligence
Artificial neural networks
Attention
Character recognition
Computation by Abstract Devices
Computational Biology/Bioinformatics
Computer Science
Correspondence
Dynamic characteristics
Handwriting
Handwriting recognition
Image enhancement
Image quality
Image restoration
Multilayer perceptrons
Multilayers
Neural networks
Semantics
Writing
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the domain of handwritten character recognition, inpainting occluded offline characters is essential. Relying on the remarkable achievements of transformers in various tasks, we present a novel framework called “Enhanced Inpainting with Multi-head Attention and stacked long short-term memory (LSTM) Network” (E-Inpaint). This framework aims to restore occluded offline handwriting while capturing its online signal counterpart, enriched with dynamic characteristics. The proposed approach employs Convolutional Neural Network (CNN) and Multi-Layer Perceptron (MLP) in order to extract essential hidden features from the handwriting image. These features are then decoded by stacked LSTM with Multi-head Attention, achieving the inpainting process and generating the online signal corresponding to the uncorrupted version. To validate our work, we utilize the recognition system Beta-GRU on Latin, Indian, and Arabic On/Off dual datasets. The obtained results show the efficiency of using stacked-LSTM network with multi-head attention, enhancing the quality of the restored image and significantly improving the recognition rate using the innovative Beta-GRU system. Our research mainly highlights the potential of E-Inpaint in enhancing handwritten character recognition systems.
ISSN:1866-9956
1866-9964
DOI:10.1007/s12559-024-10382-1