Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
Jingye Chen, Haiyang Yu, Jianqi Ma, Bin Li, Xiangyang Xue

TL;DR
This paper introduces a stroke-aware super-resolution method for scene text images, leveraging stroke-level details inspired by Gestalt Psychology to improve recognition accuracy without increasing inference time.
Contribution
The proposed method incorporates a Stroke-Focused Module that uses stroke-level attention maps to enhance super-resolution of text images, a novel approach in scene text image enhancement.
Findings
Generated images are more distinguishable and clearer.
Improved recognition accuracy on TextZoom and Degraded-IC13 datasets.
No additional inference time overhead.
Abstract
In the last decade, the blossom of deep learning has witnessed the rapid development of scene text recognition. However, the recognition of low-resolution scene text images remains a challenge. Even though some super-resolution methods have been proposed to tackle this problem, they usually treat text images as general images while ignoring the fact that the visual quality of strokes (the atomic unit of text) plays an essential role for text recognition. According to Gestalt Psychology, humans are capable of composing parts of details into the most similar objects guided by prior knowledge. Likewise, when humans observe a low-resolution text image, they will inherently use partial stroke-level details to recover the appearance of holistic characters. Inspired by Gestalt Psychology, we put forward a Stroke-Aware Scene Text Image Super-Resolution method containing a Stroke-Focused Module…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsAdvanced Image Processing Techniques · Image Processing Techniques and Applications · Image and Video Stabilization
