AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
With SynthText pre-training, the F-measure of Pixel Aggregation Network-320 boosting to 79.9%, and the best F-measure achieve by PAN-640 is 85.0%, which is 2.1% better than second-best SPCNet

Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network.

2991626090, pp.8440-8449, (2019)

Cited by: 13|Views146
Full Text
Bibtex
Weibo

Abstract

Scene text detection, an important step of scene text reading systems, has witnessed rapid development with convolutional neural networks. Nonetheless, two main challenges still exist and hamper its deployment to real-world applications. The first problem is the trade-off between speed and accuracy. The second one is to model the arbitr...More

Code:

Data:

0
Introduction
  • Scene text detection is a fundamental and critical task in computer vision, as it is a key step in many text-related applications, such as text recognition, text retrieval, license plate recognition and text visual question answering.
  • Arbitrary-shaped text detection, one of the most challenging tasks in text detection, is receiving more and more research attention Some new methods [31, 35, 50, 24] have been put forward to detect curve text instance.
  • Many of these methods Input Image Semantic.
Highlights
  • Scene text detection is a fundamental and critical task in computer vision, as it is a key step in many text-related applications, such as text recognition, text retrieval, license plate recognition and text visual question answering
  • Here we propose an arbitraryshaped text detector, namely Pixel Aggregation Network (PAN), which can achieve a good balance between speed and performance
  • We propose a low computation-cost segmentation head, which is composed of two modules: Feature Pyramid Enhancement Module (FPEM) and Feature Fusion Module (FFM)
  • With SynthText pre-training, the F-measure of PAN-320 boosting to 79.9%, and the best F-measure achieve by PAN-640 is 85.0%, which is 2.1% better than second-best SPCNet [50]
  • The performance on CTW1500 and Total-Text demonstrates the solid superiority of the proposed PAN to detect arbitrary-shaped text instances
  • We illustrate several challenging results in Fig. 6 (e)(f), which clearly demonstrate that PAN can elegantly distinguish very complex curve text instances
Methods
  • (d) of BiSeNet to ResNet18 and use one of default settings of CU-Net, which has the similar speed with the method.
  • As demonstrated in previous experiments, the proposed PAN works well in most cases of arbitrary-shaped text detection.
  • It still fails for some difficult cases, such as large character spacing (see Fig. 7 (a)), symbols (see Fig. 7 (b)) and false positives (see Fig. 7 (c)(d)).
  • For symbol detection and false positives, PAN is trained on small datasets and the authors believe this problem will be alleviated when increasing training data
Results
  • More Detected Results on

    CTW1500, Total Text, ICDAR 2015 and MSRA-TD500

    the authors show more test examples produced by PAN on different datasets in Fig. 8 (CTW1500) Fig. 9 (Total-Text), Fig. (ICDAR 2015) and Fig. (MSRATD500).
  • CTW1500, Total Text, ICDAR 2015 and MSRA-TD500.
  • The authors show more test examples produced by PAN on different datasets in Fig. 8 (CTW1500) Fig. 9 (Total-Text), Fig. (ICDAR 2015) and Fig. (MSRATD500).
  • From these results, the authors can find that the proposed PAN have the following abilities: i) separating adjacent text instances with narrow distances; ii) locating the arbitraryshaped text instances precisely; iii) detecting the text instances with various orientations; iv) detecting the long text instances; v) detecting the multiple Lingual text.
  • Thanks to the strong feature representation, PAN can locate the text instances with complex and unstable illumination, different colors and variable scales
Conclusion
  • Similar conclusions can be obtained on Total

    Text. Without external data pre-training, the speed of PAN-320 is real-time (82.4 FPS) while the performance is still very competitive (77.1%), and PAN-640 achieves the F-measure of 83.5%, surpassing all other state-of-the-art methods (including those with external data) over 0.6%.
  • Without external data pre-training, the speed of PAN-320 is real-time (82.4 FPS) while the performance is still very competitive (77.1%), and PAN-640 achieves the F-measure of 83.5%, surpassing all other state-of-the-art methods over 0.6%.
  • The performance on CTW1500 and Total-Text demonstrates the solid superiority of the proposed PAN to detect arbitrary-shaped text instances.
  • The authors illustrate several challenging results in Fig. 6 (e)(f), which clearly demonstrate that PAN can elegantly distinguish very complex curve text instances
Summary
  • Introduction:

    Scene text detection is a fundamental and critical task in computer vision, as it is a key step in many text-related applications, such as text recognition, text retrieval, license plate recognition and text visual question answering.
  • Arbitrary-shaped text detection, one of the most challenging tasks in text detection, is receiving more and more research attention Some new methods [31, 35, 50, 24] have been put forward to detect curve text instance.
  • Many of these methods Input Image Semantic.
  • Methods:

    (d) of BiSeNet to ResNet18 and use one of default settings of CU-Net, which has the similar speed with the method.
  • As demonstrated in previous experiments, the proposed PAN works well in most cases of arbitrary-shaped text detection.
  • It still fails for some difficult cases, such as large character spacing (see Fig. 7 (a)), symbols (see Fig. 7 (b)) and false positives (see Fig. 7 (c)(d)).
  • For symbol detection and false positives, PAN is trained on small datasets and the authors believe this problem will be alleviated when increasing training data
  • Results:

    More Detected Results on

    CTW1500, Total Text, ICDAR 2015 and MSRA-TD500

    the authors show more test examples produced by PAN on different datasets in Fig. 8 (CTW1500) Fig. 9 (Total-Text), Fig. (ICDAR 2015) and Fig. (MSRATD500).
  • CTW1500, Total Text, ICDAR 2015 and MSRA-TD500.
  • The authors show more test examples produced by PAN on different datasets in Fig. 8 (CTW1500) Fig. 9 (Total-Text), Fig. (ICDAR 2015) and Fig. (MSRATD500).
  • From these results, the authors can find that the proposed PAN have the following abilities: i) separating adjacent text instances with narrow distances; ii) locating the arbitraryshaped text instances precisely; iii) detecting the text instances with various orientations; iv) detecting the long text instances; v) detecting the multiple Lingual text.
  • Thanks to the strong feature representation, PAN can locate the text instances with complex and unstable illumination, different colors and variable scales
  • Conclusion:

    Similar conclusions can be obtained on Total

    Text. Without external data pre-training, the speed of PAN-320 is real-time (82.4 FPS) while the performance is still very competitive (77.1%), and PAN-640 achieves the F-measure of 83.5%, surpassing all other state-of-the-art methods (including those with external data) over 0.6%.
  • Without external data pre-training, the speed of PAN-320 is real-time (82.4 FPS) while the performance is still very competitive (77.1%), and PAN-640 achieves the F-measure of 83.5%, surpassing all other state-of-the-art methods over 0.6%.
  • The performance on CTW1500 and Total-Text demonstrates the solid superiority of the proposed PAN to detect arbitrary-shaped text instances.
  • The authors illustrate several challenging results in Fig. 6 (e)(f), which clearly demonstrate that PAN can elegantly distinguish very complex curve text instances
Tables
  • Table1: The results of models with different number of cascaded
  • Table2: The comparison between “ResNet18 + 2 FPEMs + FFM”
  • Table3: The results of models with different settings. “Fuse”
  • Table4: The single-scale results on CTW1500. “P”, “R” and “F”
  • Table5: The single-scale results on Total-Text. “P”, “R” and “F”
  • Table6: The single-scale results on ICDAR 2015. “P”, “R” and
  • Table7: The single-scale results on MSRA-TD500
  • Table8: Time consumption of PAN on CTW-1500. The total time consists of backbone, segmentation head and post-processing. “F”
  • Table9: Cross-dataset results of PAN on word-level and line-level datasets. “P”, “R” and “F” represent the precision, recall and F-
  • Table10: The results on CTW1500 of different segmentation methods. “F” means F-measure. “Ext.” indicates external data
Download tables as Excel
Related work
  • In recent years, text detectors based on deep learning have achieved remarkable results. Most of these methods can be roughly divided into two categories: anchor-based methods and anchor-free methods. Among these methods, some use a heavy framework or complicated pipeline for high accuracy, while others adopt a simple structure to maintain a good balance between speed and accuracy.

    Anchor-based text detectors are usually inspired by object detectors such as Faster R-CNN [41] and SSD [41]. TextBoxes [27] directly modifies the anchor scales and shape of convolution kernels of SSD to handle text with extreme aspect ratios. TextBoxes++ [26] further regresses quadrangles instead of horizontal bounding boxes for multioriented text detection. RRD [28] applies rotation-invariant and sensitive features for text classification and regression from two separate branches for better long text detection. SSTD [16] generates text attention map to enhance the text region of the feature map and suppress background information, which is beneficial for tiny texts. Based on Faster R-CNN, RRPN [38] develops rotated region proposals to detect titled text. Mask Text Spotter [36] and SPCNet [50] regard text detection as an instance segmentation problem and use Mask R-CNN [12] for arbitrary text detection. The above-mentioned methods achieve remarkable results on several benchmarks. Nonetheless, most of them rely on complex anchor setting, which makes these approaches heavy-footed and prevent them from applying to real-world problems.
Funding
  • This work is supported by the Natural Science Foundation of China under Grant 61672273 and Grant 61832008, the Science Foundation for Distinguished Young Scholars of Jiangsu under Grant BK20160021, and Scientific Foundation of State Grid Corporation of China (Research on Icewind Disaster Feature Recognition and Prediction by Fewshot Machine Learning in Transmission Lines)
Reference
  • Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587, 2017.
    Findings
  • Chee Kheng Ch’ng and Chee Seng Chan. Total-text: A comprehensive dataset for scene text detection and recognition. In Proc. Int. Conf. Document Analysis Recogn., 2017.
    Google ScholarLocate open access versionFindings
  • Dan Deng, Haifeng Liu, Xuelong Li, and Deng Cai. Pixellink: Detecting scene text via instance segmentation. In Proc. AAAI Conf. Artificial Intell., 2018.
    Google ScholarLocate open access versionFindings
  • Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2009.
    Google ScholarLocate open access versionFindings
  • Deng-Ping Fan, Ming-Ming Cheng, Jiang-Jiang Liu, ShangHua Gao, Qibin Hou, and Ali Borji. Salient objects in clutter: Bringing salient object detection to the foreground. In Proc. Eur. Conf. Comp. Vis., 2018.
    Google ScholarLocate open access versionFindings
  • Deng-Ping Fan, Ming-Ming Cheng, Yun Liu, Tao Li, and Ali Borji. Structure-measure: A new way to evaluate foreground maps. In Proc. IEEE Int. Conf. Comp. Vis., 2017.
    Google ScholarLocate open access versionFindings
  • Deng-Ping Fan, Cheng Gong, Yang Cao, Bo Ren, MingMing Cheng, and Ali Borji. Enhanced-alignment measure for binary foreground map evaluation. arXiv preprint arXiv:1805.10421, 2018.
    Findings
  • Deng-Ping Fan, Zheng Lin, Jia-Xing Zhao, Yun Liu, Zhao Zhang, Qibin Hou, Menglong Zhu, and Ming-Ming Cheng. Rethinking rgb-d salient object detection: Models, datasets, and large-scale benchmarks. arXiv preprint arXiv:1907.06781, 2019.
    Findings
  • Deng-Ping Fan, Wenguan Wang, Ming-Ming Cheng, and Jianbing Shen. Shifting more attention to video salient object detection. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2019.
    Google ScholarLocate open access versionFindings
  • Ankush Gupta, Andrea Vedaldi, and Andrew Zisserman. Synthetic data for text localisation in natural images. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2016.
    Google ScholarLocate open access versionFindings
  • Kaiming He, Georgia Gkioxari, Piotr Dollar, and Ross Girshick. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017.
    Google ScholarLocate open access versionFindings
  • Kaiming He, Georgia Gkioxari, Piotr Dollar, and Ross Girshick. Mask R-CNN. In Proc. IEEE Int. Conf. Comp. Vis., pages 2961–2969, 2017.
    Google ScholarLocate open access versionFindings
  • Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proc. IEEE Int. Conf. Comp. Vis., 2015.
    Google ScholarLocate open access versionFindings
  • Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2016.
    Google ScholarLocate open access versionFindings
  • Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Identity mappings in deep residual networks. In Proc. Eur. Conf. Comp. Vis., 2016.
    Google ScholarLocate open access versionFindings
  • Pan He, Weilin Huang, Tong He, Qile Zhu, Yu Qiao, and Xiaolin Li. Single shot text detector with regional attention. In Proc. IEEE Int. Conf. Comp. Vis., 2017.
    Google ScholarLocate open access versionFindings
  • Wenhao He, Xu-Yao Zhang, Fei Yin, and Cheng-Lin Liu. Deep direct regression for multi-oriented scene text detection. In Proc. IEEE Int. Conf. Comp. Vis., 2017.
    Google ScholarLocate open access versionFindings
  • Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
    Findings
  • Han Hu, Chengquan Zhang, Yuxuan Luo, Yuzhuo Wang, Junyu Han, and Errui Ding. Wordsup: Exploiting word annotations for character based text detection. In Proc. IEEE Int. Conf. Comp. Vis., 2017.
    Google ScholarLocate open access versionFindings
  • Gao Huang, Zhuang Liu, Kilian Q Weinberger, and Laurens van der Maaten. Densely connected convolutional networks. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2017.
    Google ScholarLocate open access versionFindings
  • Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167, 2015.
    Findings
  • Dimosthenis Karatzas, Lluis Gomez-Bigorda, Anguelos Nicolaou, Suman Ghosh, Andrew Bagdanov, Masakazu Iwamura, Jiri Matas, Lukas Neumann, Vijay Ramaseshan Chandrasekhar, Shijian Lu, et al. Icdar 2015 competition on robust reading. In Proc. Int. Conf. Document Analysis Recogn., 2015.
    Google ScholarLocate open access versionFindings
  • Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998.
    Google ScholarLocate open access versionFindings
  • Xiang Li, Wenhai Wang, Wenbo Hou, Ruo-Ze Liu, Tong Lu, and Jian Yang. Shape robust text detection with progressive scale expansion network. arXiv preprint arXiv:1806.02559, 2018.
    Findings
  • Xiang Li, Wenhai Wang, Xiaolin Hu, and Jian Yang. Selective kernel networks. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2019.
    Google ScholarLocate open access versionFindings
  • Minghui Liao, Baoguang Shi, and Xiang Bai. Textboxes++: A single-shot oriented scene text detector. IEEE Trans. Image Process., 2018.
    Google ScholarLocate open access versionFindings
  • Minghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, and Wenyu Liu. Textboxes: A fast text detector with a single deep neural network. In Proc. AAAI Conf. Artificial Intell., 2017.
    Google ScholarLocate open access versionFindings
  • Minghui Liao, Zhen Zhu, Baoguang Shi, Gui-song Xia, and Xiang Bai. Rotation-sensitive regression for oriented scene text detection. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2018.
    Google ScholarLocate open access versionFindings
  • Tsung-Yi Lin, Piotr Dollar, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. Feature pyramid networks for object detection. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2017.
    Google ScholarLocate open access versionFindings
  • Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. Ssd: Single shot multibox detector. In Proc. Eur. Conf. Comp. Vis., 2016.
    Google ScholarLocate open access versionFindings
  • Yuliang Liu, Lianwen Jin, Shuaitao Zhang, and Sheng Zhang. Detecting curve text in the wild: New dataset and new solution. 2017.
    Google ScholarFindings
  • Zichuan Liu, Guosheng Lin, Sheng Yang, Jiashi Feng, Weisi Lin, and Wang Ling Goh. Learning markov clustering networks for scene text detection. Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2018.
    Google ScholarLocate open access versionFindings
  • Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3431–3440, 2015.
    Google ScholarLocate open access versionFindings
  • Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2015.
    Google ScholarLocate open access versionFindings
  • Shangbang Long, Jiaqiang Ruan, Wenjie Zhang, Xin He, Wenhao Wu, and Cong Yao. Textsnake: A flexible representation for detecting text of arbitrary shapes. Proc. Eur. Conf. Comp. Vis., 2018.
    Google ScholarLocate open access versionFindings
  • Pengyuan Lyu, Minghui Liao, Cong Yao, Wenhao Wu, and Xiang Bai. Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. In Proc. Eur. Conf. Comp. Vis., 2018.
    Google ScholarLocate open access versionFindings
  • Pengyuan Lyu, Cong Yao, Wenhao Wu, Shuicheng Yan, and Xiang Bai. Multi-oriented scene text detection via corner localization and region segmentation. arXiv preprint arXiv:1802.08948, 2018.
    Findings
  • Jianqi Ma, Weiyuan Shao, Hao Ye, Li Wang, Hong Wang, Yingbin Zheng, and Xiangyang Xue. Arbitrary-oriented scene text detection via rotation proposals. IEEE Transactions on Multimedia, 2018.
    Google ScholarLocate open access versionFindings
  • Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In Proc. Int. Conf. 3D Vision, 2016.
    Google ScholarLocate open access versionFindings
  • Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. Automatic differentiation in pytorch. 2017.
    Google ScholarFindings
  • Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In Proc. Advances in Neural Inf. Process. Syst., 2015.
    Google ScholarLocate open access versionFindings
  • Baoguang Shi, Xiang Bai, and Serge Belongie. Detecting oriented text in natural images by linking segments. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2017.
    Google ScholarLocate open access versionFindings
  • Abhinav Shrivastava, Abhinav Gupta, and Ross Girshick. Training region-based object detectors with online hard example mining. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2016.
    Google ScholarLocate open access versionFindings
  • Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. In Proc. Int. Conf. Learn. Representations, 2015.
    Google ScholarLocate open access versionFindings
  • Ilya Sutskever, James Martens, George Dahl, and Geoffrey Hinton. On the importance of initialization and momentum in deep learning. In ICML, 2013.
    Google ScholarFindings
  • Zhiqiang Tang, Xi Peng, Shijie Geng, Yizhe Zhu, and Dimitris Metaxas. Cu-net: Coupled u-nets. In BMVC, 2018.
    Google ScholarLocate open access versionFindings
  • Zhi Tian, Weilin Huang, Tong He, Pan He, and Yu Qiao. Detecting text in natural image with connectionist text proposal network. In Proc. Eur. Conf. Comp. Vis., 2016.
    Google ScholarLocate open access versionFindings
  • Wenhai Wang, Xiang Li, Tong Lu, and Jian Yang. Mixed link networks. In Proc. Int. Joint Conf. Artificial Intell., 2018.
    Google ScholarLocate open access versionFindings
  • Svante Wold, Kim Esbensen, and Paul Geladi. Principal component analysis. Chemometrics and Intelligent Laboratory Systems, 2(1-3):37–52, 1987.
    Google ScholarLocate open access versionFindings
  • Enze Xie, Yuhang Zang, Shuai Shao, Gang Yu, Cong Yao, and Guangyao Li. Scene text detection with supervised pyramid context network. In Proc. AAAI Conf. Artificial Intell., 2019.
    Google ScholarLocate open access versionFindings
  • Cong Yao, Xiang Bai, and Wenyu Liu. A unified framework for multioriented text detection and recognition. IEEE Transactions on Image Processing, 23(11):4737–4749, 2014.
    Google ScholarLocate open access versionFindings
  • Cong Yao, Xiang Bai, Wenyu Liu, Yi Ma, and Zhuowen Tu. Detecting texts of arbitrary orientations in natural images. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2012.
    Google ScholarLocate open access versionFindings
  • Cong Yao, Xiang Bai, Nong Sang, Xinyu Zhou, Shuchang Zhou, and Zhimin Cao. Scene text detection via holistic, multi-channel prediction. arXiv preprint arXiv:1606.09002, 2016.
    Findings
  • Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, and Nong Sang. Bisenet: Bilateral segmentation network for real-time semantic segmentation. In Proc. Eur. Conf. Comp. Vis., 2018.
    Google ScholarLocate open access versionFindings
  • Zheng Zhang, Chengquan Zhang, Wei Shen, Cong Yao, Wenyu Liu, and Xiang Bai. Multi-oriented text detection with fully convolutional networks. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2016.
    Google ScholarLocate open access versionFindings
  • Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, and Jiaya Jia. Pyramid scene parsing network. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2017.
    Google ScholarLocate open access versionFindings
  • Jia-Xing Zhao, Yang Cao, Deng-Ping Fan, Ming-Ming Cheng, Xuan-Yi Li, and Le Zhang. Contrast prior and fluid pyramid integration for rgbd salient object detection. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2019.
    Google ScholarLocate open access versionFindings
  • Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, and Jiajun Liang. East: an efficient and accurate scene text detector. arXiv preprint arXiv:1704.03155, 2017.
    Findings
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科