Text detection and removal from image using inpainting with smoothing

Wagh, Priyanka Deelip; Patil, D. R.

doi:10.1109/pervasive.2015.7087154

Cited by 20 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early text erasing research starts with the removal of borndigital text such as watermarks, captions, and subtitles on images or video sequences [39]. Owing to the plain layout, color, and regular font, born-digital text can be detected by traditional feature engineering approaches, such as binarization [40], [41], and inpainted by patch matching [42] or smoothing algorithm [43].…”

Section: Text Erasingmentioning

confidence: 99%

Stroke-Based Scene Text Erasing Using Synthetic Data for Training

Tang,

Miyazaki,

Sugaya

et al. 2021

Preprint

View full text Add to dashboard Cite

Scene text erasing, which replaces text regions with reasonable content in natural images, has drawn attention in the computer vision community in recent years. There are two potential subtasks in scene text erasing: text detection and image inpainting. Either sub-task requires considerable data to achieve better performance; however, the lack of a large-scale real-world scene-text removal dataset allows the existing methods to not work in full strength. To avoid the limitation of the lack of pairwise real-world data, we enhance and make full use of the synthetic text and consequently train our model only on the dataset generated by the improved synthetic text engine. Our proposed network contains a stroke mask prediction module and background inpainting module that can extract the text stroke as a relatively small hole from the text image patch to maintain more background content for better inpainting results. This model can partially erase text instances in a scene image with a bounding box provided or work with an existing scene text detector for automatic scene text erasing. The experimental results of qualitative evaluation and quantitative evaluation on the SCUT-Syn, ICDAR2013, and SCUT-EnsText datasets demonstrate that our method significantly outperforms existing state-of-the-art methods even when trained on real-world data.

show abstract

Section: Text Erasingmentioning

confidence: 99%

Stroke-Based Scene Text Erasing Using Synthetic Data for Training

Tang,

Miyazaki,

Sugaya

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, several methods have been proposed to remove graphic text from born-digital images such as captions, subtitles, and annotations (Khodadadi and Behrad 2012;Modha and Dave 2014;Wagh and Patil 2015). However, these methods required the text to be axis-aligned, clean, and well focused, therefore they are not applicable to scene text erasing because of its complexities, uneven illuminations, perspective distortions, etc.…”

Section: Related Workmentioning

confidence: 99%

EnsNet: Ensconce Text in the Wild

Zhang

Liu

Jin

et al. 2019

AAAI

View full text Add to dashboard Cite

A new method is proposed for removing text from natural images. The challenge is to first accurately localize text on the stroke-level and then replace it with a visually plausible background. Unlike previous methods that require image patches to erase scene text, our method, namely ensconce network (EnsNet), can operate end-to-end on a single image without any prior knowledge. The overall structure is an end-to-end trainable FCN-ResNet-18 network with a conditional generative adversarial network (cGAN). The feature of the former is first enhanced by a novel lateral connection structure and then refined by four carefully designed losses: multiscale regression loss and content loss, which capture the global discrepancy of different level features; texture loss and total variation loss, which primarily target filling the text region and preserving the reality of the background. The latter is a novel local-sensitive GAN, which attentively assesses the local consistency of the text erased regions. Both qualitative and quantitative sensitivity experiments on synthetic images and the ICDAR 2013 dataset demonstrate that each component of the EnsNet is essential to achieve a good performance. Moreover, our EnsNet can significantly outperform previous state-of-the-art methods in terms of all metrics. In addition, a qualitative experiment conducted on the SMBNet dataset further demonstrates that the proposed method can also preform well on general object (such as pedestrians) removal tasks. EnsNet is extremely fast, which can preform at 333 fps on an i5-8600 CPU device.

show abstract

“…Two-step approaches remove text by inpainting text located with a text detection algorithm. Early two-step approaches [4,9] are mainly based-on primitive hand-crafted text-detection and inpainting algorithms. A recent two-step approach with more accurate text localization is proposed by Tursun et al [8].…”

Section: Related Workmentioning

confidence: 99%

MTRNet: A Generic Scene Text Eraser

Tursun

Zeng

Denman

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

Text removal algorithms have been proposed for unilingual scripts with regular shapes and layouts. However, to the best of our knowledge, a generic text removal method which is able to remove all or user-specified text regions regardless of font, script, language or shape is not available. Developing such a generic text eraser for real scenes is a challenging task, since it inherits all the challenges of multi-lingual and curved text detection and inpainting. To fill this gap, we propose a mask-based text removal network (MTRNet). MTRNet is a conditional adversarial generative network (cGAN) with an auxiliary mask. The introduced auxiliary mask not only makes the cGAN a generic text eraser, but also enables stable training and early convergence on a challenging large-scale synthetic dataset, initially proposed for text detection in real scenes. What's more, MTRNet achieves state-of-the-art results on several real-world datasets including ICDAR 2013, ICDAR 2017 MLT, and CTW1500, without being explicitly trained on this data, outperforming previous state-of-the-art methods trained directly on these datasets.

show abstract

Text detection and removal from image using inpainting with smoothing

Cited by 20 publications

References 5 publications

Stroke-Based Scene Text Erasing Using Synthetic Data for Training

Stroke-Based Scene Text Erasing Using Synthetic Data for Training

EnsNet: Ensconce Text in the Wild

MTRNet: A Generic Scene Text Eraser

Contact Info

Product

Resources

About