IFR: Iterative Fusion Based Recognizer For Low Quality Scene Text Recognition
This work addresses the challenge of recognizing low-quality text in real-world scenes, which is crucial for applications like document scanning and autonomous systems, but it appears incremental as it builds on existing deep learning methods with iterative fusion.
The paper tackles low-quality scene text recognition by proposing an Iterative Fusion based Recognizer (IFR) that integrates image recovery and recognition branches, achieving significant improvements in recognition accuracy on benchmark datasets and low-resolution images in the TextZoom dataset.
Although recent works based on deep learning have made progress in improving recognition accuracy on scene text recognition, how to handle low-quality text images in end-to-end deep networks remains a research challenge. In this paper, we propose an Iterative Fusion based Recognizer (IFR) for low quality scene text recognition, taking advantage of refined text images input and robust feature representation. IFR contains two branches which focus on scene text recognition and low quality scene text image recovery respectively. We utilize an iterative collaboration between two branches, which can effectively alleviate the impact of low quality input. A feature fusion module is proposed to strengthen the feature representation of the two branches, where the features from the Recognizer are Fused with image Restoration branch, referred to as RRF. Without changing the recognition network structure, extensive quantitative and qualitative experimental results show that the proposed method significantly outperforms the baseline methods in boosting the recognition accuracy of benchmark datasets and low resolution images in TextZoom dataset.