Multi-task learning for scene text image super-resolution with multiple transformers

• Main Authors: Honda, Kosuke, Kurematsu, Masaki, Fujita, Hamido, Selamat, Ali
• Format: Article
• Language: English
• Published: MDPI 2022
• Subjects: T Technology (General)
• Online Access: http://eprints.utm.my/103563/1/AliSelamat2022_MultiTaskLearningforSceneTextImage.pdf; http://eprints.utm.my/103563/; http://dx.doi.org/10.3390/electronics11223813

Scene text image super-resolution aims to improve readability by recovering text shapes from low-resolution degraded text images. Although recent developments in deep learning have greatly improved super-resolution (SR) techniques, recovering text images with irregular shapes, heavy noise, and blurr...