Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

A deep learning approach for robust, multi-oriented, and curved text detection

Ranjbarzadeh, Ramin orcid logoORCID: 0000-0001-7065-9060, Ghoushchi, Saeid Jafarzadeh orcid logoORCID: 0000-0003-3665-9010, Anari, Shokofeh, Safavi, Sadaf orcid logoORCID: 0000-0003-4852-7138, Sarshar, Nazanin Tataei, Tirkolaee, Erfan Babaee orcid logoORCID: 0000-0003-1664-9210 and Bendechache, Malika orcid logoORCID: 0000-0003-0069-1860 (2022) A deep learning approach for robust, multi-oriented, and curved text detection. Cognitive Computation . ISSN 1866-9956

Abstract
Automatic text localization and segmentation in a normal environment with vertical or curved texts are core elements of numerous tasks comprising the identification of vehicles and self-driving cars, and preparing significant information from real scenes to visually impaired people. Nevertheless, texts in the real environment can be discovered with a high level of angles, profiles, dimensions, and colors which is an arduous process to detect. In this paper, a new framework based on a convolutional neural network (CNN) is introduced to obtain high efficiency in detecting text even in the presence of a complex background. Due to using a new inception layer and an improved ReLU layer, an excellent result is gained to detect text even in the presence of complex backgrounds. At first, four new m.ReLU layers are employed to explore low-level visual features. The new m.ReLU building block and inception layer are optimized to detect vital information maximally. The effect of stacking up inception layers (kernels with the dimension of 3 × 3 or bigger) is explored and it is demonstrated that this strategy is capable of obtaining mostly varying-sized texts further successfully than a linear chain of convolution layers (Conv layers). The suggested text detection algorithm is conducted in four well-known databases, namely ICDAR 2013, ICDAR 2015, ICDAR 2017, and ICDAR 2019. Text detection results on all mentioned databases with the highest recall of 94.2%, precision of 95.6%, and F-score of 94.8% illustrate that the developed strategy outperforms the state-of-the-art frameworks.
Metadata
Item Type:Article (Published)
Refereed:Yes
Uncontrolled Keywords:Deep learning; Text detection; Curved texts; Convolutional neural networks; Text segmentation
Subjects:Computer Science > Artificial intelligence
Computer Science > Machine translating
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > Lero: The Irish Software Engineering Research Centre
Research Initiatives and Centres > ADAPT
Publisher:Springer
Official URL:https://dx.doi.org/10.1007/s12559-022-10072-w
Copyright Information:© 2022 Springer
Funders:Science Foundation Ireland under grant number no. 18/CRT/6183, Science Foundation Ireland under grant number no. (grant 13/RC/2106/_P2) ADAPT &(grant 13/RC/2094/_P2) LERO, European Regional Development Fund
ID Code:28040
Deposited On:20 Jan 2023 13:28 by Annalina Caputo . Last Modified 14 Nov 2023 04:30
Documents

Full text available as:

[thumbnail of A deep learning approach for robust multi oriented and curved text detection.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution-Noncommercial-No Derivative Works 3.0
1MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record