EraseNet: End-to-End Text Removal in the Wild

Liu, Chongyu; Liu, Yuliang; Jin, Lianwen; Zhang, Shuaitao; Luo, Canjie; Wang, Yongpan

doi:10.1109/tip.2020.3018859

Cited by 48 publications

(73 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, EnsNet [1] trained its model on linearly oriented alphanumeric text, but to generalize the method for use on multi-lingual and curved text, additional costly annotation efforts are required to generate image pairs with and without such text. Other notable and recent scene text removal works are [26], [27] with additional text segmentation and GAN [28]-based inpainting approach. These methods also achieve scene text removal in good quality, but a quantitative comparison is limited as targeting dataset is different.…”

Section: Related Workmentioning

confidence: 99%

Detecting and Removing Text in the Wild

Cho¹,

Yun

Han

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Scene text removal is a challenging task that aims to erase wild text regions that include text strokes and their ambiguous boundaries, such as embossing, shade, or flare. The challenging issues raised in the wild are not completely addressed by the existing methods. To address these issues, we propose a new loss function for blending two tasks in a new network structure that depicts wild text regions in a soft mask and selectively inpaints them into a sensible background. The proposed loss function aids the learning of two seemingly separate tasks in a synergistic way via the soft mask to achieve remarkable performance in scene text removal. We validate our method through qualitative and quantitative comparisons, and region-wise analysis, showing that our method outperforms existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Detecting and Removing Text in the Wild

Cho¹,

Yun

Han

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Zdenek et al [7] proposed a weak supervision method employing a pretrained scene text detector [28] and image inpainting model [45] that do not require paired-wise training data of scene images with text and their corresponding text-erased images. Liu et al [4] provided a comprehensive real-world scenetext removal benchmark, named SCUT-EnsText, and proposed EraseNet adopting a coarse-to-fine erasure network structure with a segmentation head, which can generate a mask of the text region to help with text region localization. MTRNet++ [2] shares the same coarse-to-fine inpainting idea but uses a multi-branch generator.…”

Section: Text Erasingmentioning

confidence: 99%

“…After the prior work of Scene Text Eraser [1], scene text erasing research has developed into two directions: one-step and two-step methods. [2]- [4] are the representative works of one-step methods combining the text detection and inpainting functions into one network, which makes one-step method Manuscript received March 10, 2021. This work was partially supported by JSPS KAKENHI Grant Numbers 18K19772, 19K12033, 20H04201.…”

Section: Introductionmentioning

confidence: 99%

“…To allow for the network to learn the complicated distribution of scene texts, a considerable number of manual text-erased real-world images are required as training data because the text distribution of the Synth-text [5] dataset, which is generated according to human rules, is significantly different from the real-world one. To generate scene-text-erased images [4], [6], photo editing software such as Photoshop is used to fill the text region with visually plausible content in natural images. However, this type of annotation is expensive and time-consuming because the annotators need to operate carefully to guarantee the erasing quality, especially when facing a text instance on a complicated background.…”

Section: Introductionmentioning

confidence: 99%

“…• We enhance Text Synthesis Engine [5] to make the appearance of synthetic text instances share more similarity with real-world data. • The quantitative and qualitative evaluation results on SCUT-Syn [3], ICDAR 2013 [10] and SCUT-EnsText [4] datasets show that our method outperforms previous stateof-the-art methods while it is only trained on the dataset generated by the improved synthetic text engine [5]. The remainder of this paper is structured as follows.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

CHENet: Image to Image Chinese Handwriting Eraser

Wang

Jin

et al. 2022

Pattern Recognition and Computer Vision

View full text Add to dashboard Cite

EraseNet: End-to-End Text Removal in the Wild

Cited by 48 publications

References 43 publications

Detecting and Removing Text in the Wild

Detecting and Removing Text in the Wild

Stroke-Based Scene Text Erasing Using Synthetic Data for Training

CHENet: Image to Image Chinese Handwriting Eraser

Contact Info

Product

Resources

About