Scene Text Detection Using Attention with Depthwise Separable Convolutions
Open Access
- 24 June 2022
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 12 (13) , 6425
Abstract
In spite of significant research efforts, the existing scene text detection methods fall short of the challenges and requirements posed in real-life applications. In natural scenes, text segments exhibit a wide range of shape complexities, scale, and font property variations, and they appear mostly incidental. Furthermore, the computational requirement of the detector is an important factor for real-time operation. To address the aforementioned issues, the paper presents a novel scene text detector using a deep convolutional network which efficiently detects arbitrary oriented and complex-shaped text segments from natural scenes and predicts quadrilateral bounding boxes around text segments. The proposed network is designed in a U-shape architecture with the careful incorporation of skip connections to capture complex text attributes at multiple scales. For addressing the computational requirement of the input processing, the proposed scene text detector uses the MobileNet model as the backbone that is designed on depthwise separable convolutions. The network design is integrated with text attention blocks to enhance the learning ability of our detector, where the attention blocks are based on efficient channel attention. The network is trained in a multi-objective formulation supported by a novel text-aware non-maximal procedure to generate final text bounding box predictions. On extensive evaluations on ICDAR2013, ICDAR2015, MSRA-TD500, and COCOText datasets, the paper reports detection F-scores of 0.910, 0.879, 0.830, and 0.617, respectively.Keywords
Funding Information
- Kuwait Foundation for the Advancement of Sciences (PR19-18QI-01)
This publication has 57 references indexed in Scilit:
- Fast R-CNN2015
- ICDAR 2015 competition on Robust Reading2015
- Strokelets: A Learned Multi-scale Representation for Scene Text Recognition2014
- Scene Text Recognition in Mobile Applications by Character Descriptor and Structure ConfigurationIEEE Transactions on Image Processing, 2014
- Text extraction from natural scene image: A surveyNeurocomputing, 2013
- Robust Text Detection in Natural Scene ImagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- ICDAR 2013 Robust Reading Competition2013
- Real-time scene text localization and recognition2012
- Automatic text detection for mobile augmented reality translation2011
- A new approach for video text detection2003