Dr Shivakumara Palaiahnakote S.Palaiahnakote@salford.ac.uk
Lecturer
A New Language-Independent Deep CNN for Scene Text Detection and Style Transfer in Social Media Images
Shivakumara, Palaiahnakote; Banerjee, Ayan; Pal, Umapada; Nandanwar, Lokesh; Lu, Tong; Liu, Cheng-Lin
Authors
Ayan Banerjee
Umapada Pal
Lokesh Nandanwar
Tong Lu
Cheng-Lin Liu
Abstract
Due to the adverse effect of quality caused by different social media and arbitrary languages in natural scenes, detecting text from social media images and transferring its style is challenging. This paper presents a novel end-to-end model for text detection and text style transfer in social media images. The key notion of the proposed work is to find dominant information, such as fine details in the degraded images (social media images), and then restore the structure of character information. Therefore, we first introduce a novel idea of extracting gradients from the frequency domain of the input image to reduce the adverse effect of different social media, which outputs text candidate points. The text candidates are further connected into components and used for text detection via a UNet++ like network with an EfficientNet backbone (EffiUNet++). Then, to deal with the style transfer issue, we devise a generative model, which comprises a target encoder and style parameter networks (TESP-Net) to generate the target characters by leveraging the recognition results from the first stage. Specifically, a series of residual mapping and a position attention module are devised to improve the shape and structure of generated characters. The whole model is trained end-to-end so as to optimize the performance. Experiments on our social media dataset, benchmark datasets of natural scene text detection and text style transfer show that the proposed model outperforms the existing text detection and style transfer methods in multilingual and cross-language scenario.
Citation
Shivakumara, P., Banerjee, A., Pal, U., Nandanwar, L., Lu, T., & Liu, C.-L. (2023). A New Language-Independent Deep CNN for Scene Text Detection and Style Transfer in Social Media Images. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 32, 3552 - 3566. https://doi.org/10.1109/TIP.2023.3287038
Journal Article Type | Article |
---|---|
Acceptance Date | Jun 23, 2023 |
Publication Date | Jun 21, 2023 |
Deposit Date | Feb 2, 2024 |
Journal | IEEE Transactions on Image Processing |
Print ISSN | 1057-7149 |
Publisher | Institute of Electrical and Electronics Engineers |
Peer Reviewed | Peer Reviewed |
Volume | 32 |
Pages | 3552 - 3566 |
DOI | https://doi.org/10.1109/TIP.2023.3287038 |
You might also like
An Adaptive Xception Model for Classification of Brain Tumors
(2024)
Journal Article
Altered Handwritten Text Detection in Document Images Using Deep Learning
(2024)
Journal Article
NDOrder: Exploring a Novel Decoding Order for Scene Text Recognition
(2024)
Journal Article
Downloadable Citations
About USIR
Administrator e-mail: library-research@salford.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2025
Advanced Search