Binary Document Image Super Resolution for Improved Readability and OCR Performance

Pandey, Ram Krishna; Vignesh, K; Ramakrishnan, A G; B, Chandrahasa

doi:10.48550/arxiv.1812.02475

Cited by 11 publications

(16 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[32] compared the performance of several artificial filters on down-sampled text images. [36] propose a convolutiontransposed convolution architecture to deal with binary document SR. [9] adapt SRCNN [8] in text image SR in the ICDAR 2015 competition TextSR [37] and achieved a good performance, but no text-oriented method was proposed.…”

Section: Related Workmentioning

confidence: 99%

Scene Text Image Super-Resolution in the Wild

Wang

Xie

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

Low-resolution text images are often seen in natural scenes such as documents captured by mobile phones. Recognizing low-resolution text images is challenging because they lose detailed content information, leading to poor recognition accuracy. An intuitive solution is to introduce super-resolution (SR) techniques as pre-processing. However, previous single image super-resolution (SISR) methods are trained on synthetic low-resolution images (e.g. Bicubic down-sampling), which is simple and not suitable for real low-resolution text recognition. To this end, we propose a real scene text SR dataset, termed TextZoom. It contains paired real low-resolution and high-resolution images which are captured by cameras with different focal length in the wild. It is more authentic and challenging than synthetic data, as shown in Fig. 1. We argue improving the recognition accuracy is the ultimate goal for Scene Text SR. In this purpose, a new Text Super-Resolution Network, termed TSRN, with three novel modules is developed. (1) A sequential residual block is proposed to extract the sequential information of the text images. (2) A boundary-aware loss is designed to sharpen the character boundaries.(3) A central alignment module is proposed to relieve the misalignment problem in TextZoom. Extensive experiments on TextZoom demonstrate that our TSRN largely improves the recognition accuracy by over 13% of CRNN, and by nearly 9.0% of ASTER and MORAN compared to synthetic SR data. Furthermore, our TSRN clearly outperforms 7 stateof-the-art SR methods in boosting the recognition accuracy of LR images in TextZoom. For example, it outperforms LapSRN by over 5% and 8% on the recognition accuracy of ASTER and CRNN. Our results suggest that low-resolution text recognition in the wild is far from being solved, thus more research effort is needed.

show abstract

Section: Related Workmentioning

confidence: 99%

Scene Text Image Super-Resolution in the Wild

Wang

Xie

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The previous super-resolution methods usually try to learn degradation patterns through HR-LR pairs with global loss functions (e.g., L1 or L2 loss) to recover every pixel in text images (Xu et al 2017;Pandey et al 2018). These methods, however, usually view text images as general images regardless of text-specific properties.…”

Section: Introductionmentioning

confidence: 99%

Text Gestalt: Stroke-Aware Scene Text Image Super-resolution

Chen

et al. 2022

AAAI

View full text Add to dashboard Cite

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 (SFM) to concentrate on stroke-level internal structures of characters in text images. Specifically, we attempt to design rules for decomposing English characters and digits at stroke-level, then pre-train a text recognizer to provide stroke-level attention maps as positional clues with the purpose of controlling the consistency between the generated super-resolution image and high-resolution ground truth. The extensive experimental results validate that the proposed method can indeed generate more distinguishable images on TextZoom and manually constructed Chinese character dataset Degraded-IC13. Furthermore, since the proposed SFM is only used to provide stroke-level guidance when training, it will not bring any time overhead during the test phase. Code is available at https://github.com/FudanVI/FudanOCR/tree/main/text-gestalt.

show abstract

“…A Lat et al [24] improved OCR accuracy by super-resolving document images using SRGAN [19]. Another closely related work, [25] uses deep neural network architectures for Binary Document Image Super-Resolution (BDISR) in Tamil script. These works are only restricted to document images, whereas our method solves a broader problem of text image SR while improving OCR confidence.…”

Section: Related Workmentioning

confidence: 99%

On-Device Text Image Super Resolution

Jain

Prabhu

Ramena

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

Recent research on super-resolution (SR) has witnessed major developments with the advancements of deep convolutional neural networks. There is a need for information extraction from scenic text images or even document images on device, most of which are low-resolution (LR) images. Therefore, SR becomes an essential pre-processing step as Bicubic Upsampling, which is conventionally present in smartphones, performs poorly on LR images. To give the user more control over his privacy, and to reduce the carbon footprint by reducing the overhead of cloud computing and hours of GPU usage, executing SR models on the edge is a necessity in the recent times. There are various challenges in running and optimizing a model on resource-constrained platforms like smartphones. In this paper, we present a novel deep neural network that reconstructs sharper character edges and thus boosts OCR confidence. The proposed architecture not only achieves significant improvement in PSNR over bicubic upsampling on various benchmark datasets but also runs with an average inference time of 11.7 ms per image. We have outperformed state-of-the-art on the Text330 dataset. We also achieve an OCR accuracy of 75.89% on the ICDAR 2015 TextSR dataset, where ground truth has an accuracy of 78.10%.

show abstract

Binary Document Image Super Resolution for Improved Readability and OCR Performance

Cited by 11 publications

References 42 publications

Scene Text Image Super-Resolution in the Wild

Scene Text Image Super-Resolution in the Wild

Text Gestalt: Stroke-Aware Scene Text Image Super-resolution

On-Device Text Image Super Resolution

Contact Info

Product

Resources

About