Filters








5,474 Hits in 5.1 sec

Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation [article]

Pengyuan Lyu, Cong Yao, Wenhao Wu, Shuicheng Yan, Xiang Bai
2018 arXiv   pre-print
We propose to detect scene text by localizing corner points of text bounding boxes and segmenting text regions in relative positions.  ...  The first category treats scene text as a type of general objects and follows general object detection paradigm to localize scene text by regressing the text box locations, but troubled by the arbitrary-orientation  ...  Conclusion In this paper, we have presented a scene text detector that localize text by corner point detection and positionsensitive segmentation.  ... 
arXiv:1802.08948v2 fatcat:hehg4vyh4ncn5hijlz3eucrkn4

Multi-oriented Scene Text Detection via Corner Localization and Region Segmentation

Pengyuan Lyu, Cong Yao, Wenhao Wu, Shuicheng Yan, Xiang Bai
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
We propose to detect scene text by localizing corner points of text bounding boxes and segmenting text regions in relative positions.  ...  The first category treats scene text as a type of general objects and follows general object detection paradigm to localize scene text by regressing the text box locations, but troubled by the arbitrary-orientation  ...  Acknowledgement This work was supported by NSFC 61733007 and 61573160, to Dr.  ... 
doi:10.1109/cvpr.2018.00788 dblp:conf/cvpr/LyuYWYB18 fatcat:i5g6ar242rdcdl6gn7y2vuh7ka

TextField: Learning A Deep Direction Field for Irregular Scene Text Detection [article]

Yongchao Xu, Yukang Wang, Wei Zhou, Yongpan Wang, Zhibo Yang, Xiang Bai
2019 arXiv   accepted
Scene text detection is an important step of scene text reading system. The main challenges lie on significantly varied sizes and aspect ratios, arbitrary orientations and shapes.  ...  Driven by recent progress in deep learning, impressive performances have been achieved for multi-oriented text detection.  ...  In [35] , Lyu et al. propose to first regress four corners of text boxes, followed by a combination of corners and Non-Maximum Suppression (NMS) process to achieve accurate multi-oriented text localization  ... 
arXiv:1812.01393v2 fatcat:npvethdp3bdmtck6bvmfx4mddi

Irregular scene text detection via attention guided border labeling

Jie Chen, Zhouhui Lian, Yizhi Wang, Yingmin Tang, Jianguo Xiao
2019 Science China Information Sciences  
To solve this problem, we propose a novel method to detect irregular scene texts based on instance-aware segmentation.  ...  respectively) and obtains comparable performance on multi-oriented text datasets compared to the state-of-the-art approaches.  ...  Acknowledgements This work was supported by National Natural Science Foundation of China (Grant Nos. 61672056, 61672043) and Key Laboratory of Science, Technology and Standard in Press Industry (Key  ... 
doi:10.1007/s11432-019-2673-8 fatcat:zwjt5pwklfgcjemiwopq5yxt4m

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

Pengyuan Lyu, Minghui Liao, Cong Yao, Wenhao Wu, Xiang Bai
2018 Lecture Notes in Computer Science  
which precise text detection and recognition are acquired via semantic segmentation.  ...  Recently, models based on deep neural networks have dominated the fields of scene text detection and recognition.  ...  Multi-oriented scene text detection has become a hot topic recently. Yao et al. [52] and Zhang et al. [55] detect multi-oriented scene text by semantic segmentation. Tian et al.  ... 
doi:10.1007/978-3-030-01264-9_5 fatcat:lk6uqziccvebbacm3qcjpepq5i

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

Pengyuan Lyu, Minghui Liao, Cong Yao, Wenhao Wu, Xiang Bai
2018 arXiv   pre-print
which precise text detection and recognition are acquired via semantic segmentation.  ...  Recently, models based on deep neural networks have dominated the fields of scene text detection and recognition.  ...  Multi-oriented scene text detection has become a hot topic recently. Yao et al. [52] and Zhang et al. [55] detect multi-oriented scene text by semantic segmentation. Tian et al.  ... 
arXiv:1807.02242v2 fatcat:lylbcy4hzrgmxmhawtxcmgc23i

Instance Segmentation Network with Selfdistillation for Scene Text Detection

Peng Yang, Guowei Yang, Xun Gong, Pingping Wu, Xu Han, Jiasong Wu, Caisen Chen
2020 IEEE Access  
Segmentation based methods have become the mainstream for detecting scene text with arbitrary orientations and shapes.  ...  ., ICDAR2015, ICDAR2017 MLT, CTW1500 and Total-Text, and the experimental results show that it can achieve better tradeoff between accuracy and efficiency for scene text detection.  ...  CLRS [37] detected scene text by localizing corner points of text bounding boxes and segmenting text regions in relative positions.  ... 
doi:10.1109/access.2020.2978225 fatcat:tylrcfwzcvfijn47dgthjnvtui

Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting [article]

Liang Qiao, Sanli Tang, Zhanzhan Cheng, Yunlu Xu, Yi Niu, Shiliang Pu, Fei Wu
2021 arXiv   pre-print
Many approaches have recently been proposed to detect irregular scene text and achieved promising results.  ...  STM) is designed to transform the detected feature regions into regular morphologies without extra parameters.  ...  (Ma et al. 2018 ) proposed a rotated regional proposal network to enhance multi-oriented text detection.  ... 
arXiv:2002.06820v2 fatcat:qv77ioltuzbuvdemmny5d4ke5a

Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting

Liang Qiao, Sanli Tang, Zhanzhan Cheng, Yunlu Xu, Yi Niu, Shiliang Pu, Fei Wu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Many approaches have recently been proposed to detect irregular scene text and achieved promising results.  ...  STM) is designed to transform the detected feature regions into regular morphologies without extra parameters.  ...  (Ma et al. 2018 ) proposed a rotated regional proposal network to enhance multi-oriented text detection.  ... 
doi:10.1609/aaai.v34i07.6864 fatcat:4jqpb3xktrc4jfvesivjs4ruoy

Industrial Scene Text Detection with Refined Feature-attentive Network [article]

Tongkun Guan, Chaochen Gu, Changsheng Lu, Jingzheng Tu, Qi Feng, Kaijie Wu, Xinping Guan
2021 arXiv   pre-print
Moreover, we construct two industrial scene text datasets, including a total of 102156 images and 1948809 text instances with various character structures and metal parts.  ...  Specifically, we design a parallel feature integration mechanism to construct an adaptive feature representation from multi-resolution features, which enhances the perception of multi-scale texts at each  ...  INTRODUCTION T HE task of text detection is to detect the text regions and localize them with bounding boxes, which mainly researches horizontal texts, multi-oriented texts, and curved texts in various  ... 
arXiv:2110.12663v1 fatcat:kfskmludrrccphhigsc7fepwki

All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting

Hao Wang, Pu Lu, Hui Zhang, Mingkun Yang, Xiang Bai, Yongchao Xu, Mengchao He, Yongpan Wang, Wenyu Liu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Different from the existing approaches that formulate text detection as bounding box extraction or instance segmentation, we localize a set of points on the boundary of each text instance.  ...  Experiments on three challenging datasets, including ICDAR2015, TotalText and COCO-Text demonstrate that the proposed method consistently surpasses the state-of-the-art in both scene text detection and  ...  .; and Luo, J. 2018. Integrating scene text and visual appearance for fine-grained image classification. IEEE Access 6:66322-66335.  ... 
doi:10.1609/aaai.v34i07.6896 fatcat:uo2z2e5wsfgyvcend2tkqdphqe

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
2019 arXiv   pre-print
end-to-end learning procedure, in which both detection and recognition can be achieved directly from two-dimensional space via semantic segmentation.  ...  In this paper, we investigate the problem of scene text spotting, which aims at simultaneous text detection and recognition in natural images.  ...  [79] detect multi-oriented scene text by semantic segmentation.  ... 
arXiv:1908.08207v1 fatcat:q7k2ejs2xfdcnighybsh6sauua

Geometry-Aware Scene Text Detection with Instance Transformation Network

Fangfang Wang, Liming Zhao, Xi Li, Xinchao Wang, Dacheng Tao
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Localizing text in the wild is challenging in the situations of complicated geometric layout of the targets like random orientation and large aspect ratio.  ...  An end-to-end multi-task learning strategy with transformation regression, text/non-text classification and coordinates regression is adopted in the ITN.  ...  Network (ITN), to effectively detect multi-scale, multi-oriented and multi-lingual scene text.  ... 
doi:10.1109/cvpr.2018.00150 dblp:conf/cvpr/WangZ0WT18 fatcat:z2ys5ri4ijhgdea3yrpaxpkode

All You Need is a Second Look: Towards Arbitrary-Shaped Text Detection [article]

Meng Cao, Can Zhang, Dongming Yang, Yuexian Zou
2021 arXiv   pre-print
Existing mainstream methods follow the instance segmentation pipeline to obtain the text regions.  ...  Compared to the traditional single-stage segmentation network, our NASK conducts the detection in a coarse-to-fine manner with the first stage segmentation spotting the rectangle text proposals and the  ...  [21] propose to detect scene texts by localizing corner points of text bounding boxes and segmenting text regions in relative positions.  ... 
arXiv:2106.12720v1 fatcat:3h3dt2ofundwrpenf2uqdgrv6a

Accurate Scene Text Detection via Scale-Aware Data Augmentation and Shape Similarity Constraint

Pengwen Dai, Yang Li, Hua Zhang, Jingzhi Li, Xiaochun Cao
2021 IEEE transactions on multimedia  
This paper presents an arbitrary-shape scene text detection method that can achieve better generalization ability and more accurate localization.  ...  SSC encourages the segmentation of text or non-text in the candidate boxes to be similar to the corresponding ground truth, which is helpful to localize more accurate boundaries for arbitrary-shape scene  ...  TEXT DATASET Total-Text AND THE MULTI-ORIENTED SCENE TEXT DATASET ICDAR2015. † DENOTES THE RESULTS FROM [8]. * MEANS MULTI-SCALE TESTING RESULTS.  ... 
doi:10.1109/tmm.2021.3073575 fatcat:r4rgthwbk5cw3boixvko3zbpoi
« Previous Showing results 1 — 15 out of 5,474 results