scholarly journals Cluttered TextSpotter: An End-to-End Trainable Light-Weight Scene Text Spotter for Cluttered Environment

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 111433-111447
Author(s):  
Randheer Bagi ◽  
Tanima Dutta ◽  
Hari Prabhat Gupta
Keyword(s):  
Light Weight ◽  
Cluttered Environment ◽  
Scene Text ◽  
End To End

End to end light weight mutual authentication scheme in IoT-based healthcare environment

2019 ◽  
Vol 6 (1) ◽  
pp. 3-13
Author(s):  
S D Suganthi ◽  
R. Anitha ◽  
V. Sureshkumar ◽  
S. Harish ◽  
S. Agalya
Keyword(s):  
Mutual Authentication ◽  
Authentication Scheme ◽  
Light Weight ◽  
Healthcare Environment ◽  
End To End

End-to-end scene text recognition using tree-structured models

2014 ◽  
Vol 47 (9) ◽  
pp. 2853-2866 ◽  
Author(s):  
Cunzhao Shi ◽  
Chunheng Wang ◽  
Baihua Xiao ◽  
Song Gao ◽  
Jinlong Hu
Keyword(s):  
Text Recognition ◽  
Scene Text ◽  
End To End ◽  
Scene Text Recognition

scholarly journals Scene text removal via cascaded text stroke detection and erasing

2021 ◽  
Vol 8 (2) ◽  
pp. 273-287
Author(s):  
Xuewei Bian ◽  
Chaoqun Wang ◽  
Weize Quan ◽  
Juntao Ye ◽  
Xiaopeng Zhang ◽  
...  
Keyword(s):  
Performance Improvement ◽  
Real World ◽  
Large Scale ◽  
State Of The Art ◽  
The State ◽  
Experimental Results ◽  
Processing Unit ◽  
Final Model ◽  
Scene Text ◽  
End To End

AbstractRecent learning-based approaches show promising performance improvement for the scene text removal task but usually leave several remnants of text and provide visually unpleasant results. In this work, a novel end-to-end framework is proposed based on accurate text stroke detection. Specifically, the text removal problem is decoupled into text stroke detection and stroke removal; we design separate networks to solve these two subproblems, the latter being a generative network. These two networks are combined as a processing unit, which is cascaded to obtain our final model for text removal. Experimental results demonstrate that the proposed method substantially outperforms the state-of-the-art for locating and erasing scene text. A new large-scale real-world dataset with 12,120 images has been constructed and is being made available to facilitate research, as current publicly available datasets are mainly synthetic so cannot properly measure the performance of different methods.

scholarly journals Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages

2021 ◽  
Author(s):  
Shota Orihashi ◽  
Yoshihiro Yamazaki ◽  
Naoki Makishima ◽  
Mana Ihori ◽  
Akihiko Takashima ◽  
...  
Keyword(s):  
Text Recognition ◽  
Scene Text ◽  
Resource Poor ◽  
End To End ◽  
Scene Text Recognition

scholarly journals EnsNet: Ensconce Text in the Wild

2019 ◽  
Vol 33 ◽  
pp. 801-808 ◽  
Author(s):  
Shuaitao Zhang ◽  
Yuliang Liu ◽  
Lianwen Jin ◽  
Yaoxiong Huang ◽  
Songxuan Lai
Keyword(s):  
Generative Adversarial Network ◽  
Local Consistency ◽  
Adversarial Network ◽  
Image Patches ◽  
Scene Text ◽  
In The Wild ◽  
Lateral Connection ◽  
Previous State ◽  
End To End ◽  
General Object

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 SBMNet 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.

Sign in / Sign up

Export Citation Format

Share Document