Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition
Preprint
Abstract
Scene text recognition is a rapidly developing field that faces numerous challenges due to the complexity and diversity of scene text, including complex backgrounds, diverse fonts, flexible arrangements, and accidental occlusions. In this paper, we propose a novel approach called Class-Aware Mask-guided feature refinement (CAM) to address these challenges. Our approach introduces canonical class-aware glyph masks generated from a standard font to effectively suppress background and text style noise, thereby enhancing feature discrimination. Additionally, we design a feature alignment and fusion module to incorporate the canonical mask guidance for further feature refinement for text recognition. By enhancing the alignment between the canonical mask feature and the text feature, the module ensures more effective fusion, ultimately leading to improved recognition performance. We first evaluate CAM on six standard text recognition benchmarks to demonstrate its effectiveness. Furthermore, CAM exhibits superiority over the state-of-the-art method by an average performance gain of 4.1% across six more challenging datasets, despite utilizing a smaller model size. Our study highlights the importance of incorporating canonical mask guidance and aligned feature refinement techniques for robust scene text recognition. The code is available at https://github.com/MelosY/CAM.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Towards open-set text recognition via label-to-prototype learningPattern Recognition, 2022
- MASTER: Multi-aspect non-local network for scene text recognitionPattern Recognition, 2021
- STAN: A sequential transformation attention-based network for scene text recognitionPattern Recognition, 2021
- Multi-branch guided attention network for irregular text recognitionNeurocomputing, 2021
- Separating Content from Style Using Adversarial Learning for Recognizing Text in the WildInternational Journal of Computer Vision, 2021
- Scene Text Detection and Recognition: The Deep Learning EraInternational Journal of Computer Vision, 2020
- Curved scene text detection via transverse and longitudinal sequence connectionPattern Recognition, 2019
- MORAN: A Multi-Object Rectified Attention Network for scene text recognitionPattern Recognition, 2019
- Scene text detection and recognition: recent advances and future trendsFrontiers of Computer Science, 2015
- A robust arbitrary text detection system for natural scene imagesExpert Systems with Applications, 2014