Filters








25,870 Hits in 10.4 sec

Scene Text Recognition from Two-Dimensional Perspective

Minghui Liao, Jian Zhang, Zhaoyi Wan, Fengming Xie, Jiajun Liang, Pengyuan Lyu, Cong Yao, Xiang Bai
<span title="2019-07-17">2019</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
In this paper, we approach scene text recognition from a two-dimensional perspective.  ...  Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem.  ...  However, different from speech, text in scene images is essentially distributed in a two-dimensional space.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33018714">doi:10.1609/aaai.v33i01.33018714</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7uuec4722ragnleqri4nqtxozy">fatcat:7uuec4722ragnleqri4nqtxozy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200307043310/https://144.208.67.177/ojs/index.php/AAAI/article/download/4895/4768" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/27/f1/27f1507d55df711c18eec63d6f353f350ff589c5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33018714"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Scene Text Recognition from Two-Dimensional Perspective [article]

Minghui Liao, Jian Zhang, Zhaoyi Wan, Fengming Xie, Jiajun Liang, Pengyuan Lyu, Cong Yao, Xiang Bai
<span title="2018-11-17">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we approach scene text recognition from a two-dimensional perspective.  ...  Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem.  ...  However, different from speech, text in scene images is essentially distributed in a two-dimensional space.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.06508v2">arXiv:1809.06508v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/visjva6s3rfu5pgsaqyc2jxdfy">fatcat:visjva6s3rfu5pgsaqyc2jxdfy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200917161731/https://arxiv.org/pdf/1809.06508v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c8/91/c891910b0f995994a614e9eae875f5d182948b95.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.06508v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Scene Text Recognition via Transformer [article]

Xinjie Feng, Hongxun Yao, Yuankai Qi, Jun Zhang, Shengping Zhang
<span title="2020-04-29">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Scene text recognition with arbitrary shape is very challenging due to large variations in text shapes, fonts, colors, backgrounds, etc.  ...  We therefore propose a simple but extremely effective scene text recognition method based on transformer [50].  ...  Related Works According to the shape of the text in an image, existing scene text recognition can be roughly grouped into two categorization: text recognition with regular shapes and text recognition with  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.08077v4">arXiv:2003.08077v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wb2svxx66rgqjnhfqclbpms73e">fatcat:wb2svxx66rgqjnhfqclbpms73e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200414222832/https://arxiv.org/pdf/2003.08077v3.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.08077v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Holistic Representation Guided Attention Network for Scene Text Recognition [article]

Lu Yang, Fan Dang, Peng Wang, Hui Li, Zhen Li, Yanning Zhang
<span title="2021-03-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we propose a simple yet strong approach for scene text recognition.  ...  With this simple design, our method achieves state-of-the-art or competitive recognition performance on the evaluated regular and irregular scene text benchmark datasets.  ...  As shown in [9] , solving the irregular text recognition problem from two dimensional perspective may yield more robust performance.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.01375v5">arXiv:1904.01375v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/v6klgi54z5edrjsh5t5o5wyduq">fatcat:v6klgi54z5edrjsh5t5o5wyduq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827212145/https://arxiv.org/pdf/1904.01375v4.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0c/c2/0cc2eb6b535bc693fd81acd33e8286f541f64978.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.01375v5" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling [article]

Shangbang Long, Yushuo Guan, Kaigui Bian, Cong Yao
<span title="2020-02-10">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Irregular scene text recognition has attracted much attention from the research community, mainly due to the complexity of shapes of text in natural scene.  ...  To tackle these issues, we propose a pair of coupling modules, termed as Character Anchoring Module (CAM) and Anchor Pooling Module (APM), to extract high-level semantics from two-dimensional space to  ...  sequence learning and two-dimensional spatial arrangement of text  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.03509v1">arXiv:2002.03509v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x6zwx6r6gzeyhjjzvfnimsmsda">fatcat:x6zwx6r6gzeyhjjzvfnimsmsda</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321081302/https://arxiv.org/pdf/2002.03509v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.03509v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning to Read Irregular Text with Attention Mechanisms

Xiao Yang, Dafang He, Zihan Zhou, Daniel Kifer, C. Lee Giles
<span title="">2017</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
We show with experiments that these two components are crucial for achieving fast convergence and high classification accuracy for irregular text recognition.  ...  Our model outperforms previous work on two irregular-text datasets: SVT-Perspective and CUTE80, and is also highly-competitive on several regular-text datasets containing primarily horizontal and frontal  ...  Acknowledgments We gratefully acknowledge partial support from NSF grant CCF 1317560 and a hardware grant from NVIDIA.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2017/458">doi:10.24963/ijcai.2017/458</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/YangHZKG17.html">dblp:conf/ijcai/YangHZKG17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xrbs4lz2yvf4jhqdednr4a52oa">fatcat:xrbs4lz2yvf4jhqdednr4a52oa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190428164726/https://www.ijcai.org/proceedings/2017/0458.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/12/59/1259f7533abe2fe85fd9dead92853e2ff07a8792.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2017/458"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Robust Scene Text Recognition with Automatic Rectification [article]

Baoguang Shi, Xinggang Wang, Pengyuan Lyu, Cong Yao, Xiang Bai
<span title="2016-04-19">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Different from those in documents, words in natural images often possess irregular shapes, which are caused by perspective distortion, curved character placement, etc.  ...  We show that the model is able to recognize several types of irregular text, including perspective text and curved text.  ...  For these reasons, scene text recognition has attracted great interest from the community [28, 37, 15] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.03915v2">arXiv:1603.03915v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bqkijrzj7vfuljrhdpttiabjna">fatcat:bqkijrzj7vfuljrhdpttiabjna</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930041014/https://arxiv.org/pdf/1603.03915v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ed/d0/edd0f6d316d33c61a4a69c9262d1b1e07a93bae6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.03915v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Robust Scene Text Recognition with Automatic Rectification

Baoguang Shi, Xinggang Wang, Pengyuan Lyu, Cong Yao, Xiang Bai
<span title="">2016</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
Different from those in documents, words in natural images often possess irregular shapes, which are caused by perspective distortion, curved character placement, etc.  ...  We show that the model is able to recognize several types of irregular text, including perspective text and curved text.  ...  For these reasons, scene text recognition has attracted great interest from the community [28, 37, 15] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2016.452">doi:10.1109/cvpr.2016.452</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/ShiWLYB16.html">dblp:conf/cvpr/ShiWLYB16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jnert3jawfbptjxojd6njyjvky">fatcat:jnert3jawfbptjxojd6njyjvky</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160909125440/http://www.cv-foundation.org:80/openaccess/content_cvpr_2016/papers/Shi_Robust_Scene_Text_CVPR_2016_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7b/2f/7b2fa30bea405f8feadd68a20aa6493dacc50fea.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2016.452"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Aggregation Cross-Entropy for Sequence Recognition [article]

Zecheng Xie, Yaoxiong Huang, Yuanzhi Zhu, Lianwen Jin, Yuliang Liu, Lele Xie
<span title="2019-04-18">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective.  ...  Furthermore, the proposed ACE loss function exhibits two noteworthy properties: (1) it can be directly applied for 2D prediction by flattening the 2D prediction into 1D prediction as the input and (2)  ...  from a brand new perspective.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.08364v2">arXiv:1904.08364v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hbdoyaoourcutbjte25lxhsp7u">fatcat:hbdoyaoourcutbjte25lxhsp7u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200831133856/https://arxiv.org/pdf/1904.08364v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/45/10/4510b784e7028236f0f3b3eb950407b2e61a2e3d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.08364v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes [article]

Minghui Liao, Pengyuan Lyu, Minghang He, Cong Yao, Wenhao Wu, Xiang Bai
<span title="2019-08-22">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Benefiting from the proposed two-dimensional representation on both detection and recognition, it easily handles text instances of irregular shapes, for instance, curved text.  ...  end-to-end learning procedure, in which both detection and recognition can be achieved directly from two-dimensional space via semantic segmentation.  ...  text, profiting from its two-dimensional representation for both detection and recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.08207v1">arXiv:1908.08207v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q7k2ejs2xfdcnighybsh6sauua">fatcat:q7k2ejs2xfdcnighybsh6sauua</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825194717/https://arxiv.org/pdf/1908.08207v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/37/54/375479213a9982ecf4363669bc36449ca11421a8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.08207v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

An Algorithm for Natural Images Text Recognition Using Four Direction Features

Min Zhang, Yujin Yan, Hai Wang, Wei Zhao
<span title="2019-08-31">2019</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ikdpfme5h5egvnwtvvtjrnntyy" style="color: black;">Electronics</a> </i> &nbsp;
Irregular text has widespread applications in multiple areas. Different from regular text, irregular text is difficult to recognize because of its various shapes and distorted patterns.  ...  This method recognizes two-dimensional text images effectively, but the text must be presented from left to right.  ...  This method recognizes two-dimensional text images effectively, but the text must be presented from left to right.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics8090971">doi:10.3390/electronics8090971</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iu2aznrz2ffghju3cxytx2k7ly">fatcat:iu2aznrz2ffghju3cxytx2k7ly</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200209192453/https://res.mdpi.com/d_attachment/electronics/electronics-08-00971/article_deploy/electronics-08-00971.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/13/8b/138b2a71392670b93e291b6111254a4e123cfd4d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics8090971"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

A Multi-Object Rectified Attention Network for Scene Text Recognition [article]

Canjie Luo, Lianwen Jin, Zenghui Sun
<span title="2019-01-10">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we thus propose a multi-object rectified attention network (MORAN) for general scene text recognition.  ...  With the rectification mechanism, the MORAN can read both regular and irregular scene text.  ...  [27] proposed a recursive recurrent network with attention modeling for scene text recognition. Yang et al. [51] addressed a two-dimensional attention mechanism. Cheng et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.03003v1">arXiv:1901.03003v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p45fzxnotrgmnnondaot7zeeq4">fatcat:p45fzxnotrgmnnondaot7zeeq4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829092735/https://arxiv.org/pdf/1901.03003v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/02/a2/02a2f9270602090f08b37d4d1725c4d700605e3b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.03003v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Glyph-driven Topology Enhancement Network for Scene Text Recognition [article]

Tongkun Guan, Chaochen Gu, Jingzheng Tu, Xue Yang, Qi Feng
<span title="2022-03-07">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Attention-based methods by establishing one-dimensional (1D) and two-dimensional (2D) mechanisms with an encoder-decoder framework have dominated scene text recognition (STR) tasks due to their capabilities  ...  Experiments demonstrate that GTEN achieves competitive performance on IIIT5K-Words, Street View Text, ICDAR-series, SVT Perspective, and CUTE80 datasets.  ...  INTRODUCTION Scene text recognition (STR) aims to recognize regular and irregular texts from multi-scene images, which is widely applied in handwriting recognition [46] , industrial print recognition  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.03382v1">arXiv:2203.03382v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/whygna53szckzclx5ujtfligfu">fatcat:whygna53szckzclx5ujtfligfu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220309135436/https://arxiv.org/pdf/2203.03382v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9e/96/9e962d1c9ada6fc1f6f4f0b62fb702bea6122287.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.03382v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Decoupled Attention Network for Text Recognition [article]

Tianwei Wang, Yuanzhi Zhu, Lianwen Jin, Canjie Luo, Xiaoxue Chen, Yaqiang Wu, Qianying Wang, Mingxiang Cai
<span title="2019-12-21">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Experimental results show that DAN achieves state-of-the-art performance on multiple text recognition tasks, including offline handwritten text recognition and regular/irregular scene text recognition.  ...  Text recognition has attracted considerable research interests because of its various applications. The cutting-edge text recognition methods are based on attention mechanisms.  ...  recognizer; (Liu, Chen, and Wong 2018) proposed to rectify text at the character level; (Yang et al. 2017) and (Liao et al. 2019) proposed to recognize text in two-dimensional perspective but character-level  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.10205v1">arXiv:1912.10205v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w46ifcgp7bdabpn7zm65u3yvwa">fatcat:w46ifcgp7bdabpn7zm65u3yvwa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321000521/https://arxiv.org/pdf/1912.10205v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.10205v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

An end-to-end text spotter with text relation networks

Jianguo Jiang, Baole Wei, Min Yu, Gang Li, Boquan Li, Chao Liu, Min Li, Weiqing Huang
<span title="2021-04-01">2021</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nvdntm3qtfcjzjwo3aacs6zhtu" style="color: black;">Cybersecurity</a> </i> &nbsp;
The relevance between texts generally lies in the scene images. From the perspective of cognitive psychology, humans often combine the nearby easy-to-recognize texts to infer the unidentifiable text.  ...  Specifically, we model the co-occurrence relationship of scene texts as a graph.  ...  Scene text spotting Initially, works such as (Liao et al. 2017) and split the text spotting process into two separate stages: text detection and text recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s42400-021-00073-x">doi:10.1186/s42400-021-00073-x</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b5qp5c5iynbufid625xt7cb7fe">fatcat:b5qp5c5iynbufid625xt7cb7fe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210407060953/https://cybersecurity.springeropen.com/track/pdf/10.1186/s42400-021-00073-x.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b6/c6/b6c618ea5b53943a3a593dfe4fb005ac662e81c0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s42400-021-00073-x"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 25,870 results