Murdoch University Research Repository

Welcome to the Murdoch University Research Repository

The Murdoch University Research Repository is an open access digital collection of research
created by Murdoch University staff, researchers and postgraduate students.

Learn more

Efficient scene text detection with textual attention tower

Zhang, L., Liu, Y., Xiao, H., Yang, L., Zhu, G., Shah, S.A.A., Bennamoun, M. and Shen, P. (2020) Efficient scene text detection with textual attention tower. In: IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP) 2020, 4 - 8 May 2020, Barcelona, Spain

Link to Published Version: https://doi.org/10.1109/ICASSP40776.2020.9054213
*Subscription may be required

Abstract

Scene text detection has received attention for years and achieved an impressive performance across various benchmarks. In this work, we propose an efficient and accurate approach to detect multi-oriented text in scene images. The proposed feature fusion mechanism allows us to use a shallower network to reduce the computational complexity. A self-attention mechanism is adopted to suppress false positive detections. Experiments on public benchmarks including ICDAR 2013, ICDAR 2015 and MSRA-TD500 show that our proposed approach can achieve better or comparable performances with fewer parameters and less computational cost.

Item Type: Conference Paper
Murdoch Affiliation(s): IT, Media and Communications
URI: http://researchrepository.murdoch.edu.au/id/eprint/59865
Item Control Page Item Control Page