Fourier Feature-based CBAM and Vision Transformer for Text Detection in Drone Images
Document Type
Conference Item
Publication Date
1-1-2023
Abstract
The use of drones for several real-world applications is increasing exponentially, especially for the purpose of monitoring, surveillance, security, etc. Most existing scene text detection methods were developed for normal scene images. This work aims to develop a model for detecting text in drone as well as scene images. To reduce the adverse effects of drone images, we explore the combination of Fourier transform and Convolutional Block Attention Module (CBAM) to enhance the degraded information in the images without affecting high-contrast images. This is because the above combination helps us to extract prominent features which represent text irrespective of degradations. Therefore, the refined features extracted from the Fourier Contouring Network (FCN) are supplied to Vision Transformer, which uses the ResNet50 as a backbone and encoder-decoder for text detection in both drone and scene images. Hence, the model is called Fourier Transform based Transformer. Experimental results on drone datasets and benchmark datasets, namely, Total-Text and ICDAR 2015 of natural scene text detection show the proposed model is effective and outperforms the state-of-the-art models.
Keywords
Scene text detection, Drone images, Deep learning, Transformer, Detection transformer
Divisions
fsktm
Funders
Technology Innovation Hub (TIH), Indian Statistical Institute. Kolkata
Volume
14194
Publisher
SPRINGER INTERNATIONAL PUBLISHING AG
Publisher Location
GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
Event Title
Document Analysis and Recognition - ICDAR 2023 Workshops, Pt II
Event Location
San Jose, California
Event Dates
24-26 August 2023
Event Type
conference
Additional Information
17th International Conference on Document Analysis and Recognition Workshop (ICDAR), San Jose, CA, AUG 24-26, 2023