白翔 ICDAR2017 OCR 讲座分享.pdf

发布时间：2022-05-31 发布人：admin 分类：说明书资料大小：25.00M 资料格式：pdf 举报版权申诉

viglyh-10783965-16359647498770045394.pdf-第1页.png

第1页 / 共65页

viglyh-10783965-16359647498770045394.pdf-第2页.png

第2页 / 共65页

viglyh-10783965-16359647498770045394.pdf-第3页.png

第3页 / 共65页

viglyh-10783965-16359647498770045394.pdf-第4页.png

第4页 / 共65页

viglyh-10783965-16359647498770045394.pdf-第5页.png

第5页 / 共65页

viglyh-10783965-16359647498770045394.pdf-第6页.png

第6页 / 共65页

viglyh-10783965-16359647498770045394.pdf-第7页.png

第7页 / 共65页

viglyh-10783965-16359647498770045394.pdf-第8页.png

第8页 / 共65页

文本预览

Huazhong University of Science & Technology Deep Neural Networks for Scene Text Reading Xiang Bai Huazhong University of Science and Technology

Problem definitions p Definitions End-to-end recognition Scene text detection Scene text recognition Summary Booklet Predicting the presence of text and localizing each instance (if any), usually at word or line level, in natural scenes Converting text regions into computer readable and editable symbols Xiang Bai, Kyoto, November 15

Outline Ø Background Ø Scene Text Detection Ø Scene Text Recognition Ø Applications Ø Future Trends Xiang Bai, Kyoto, November 15

Background Document image VS Scene text image p Scattered and sparse p Multi-oriented p Multi-lingual Xiang Bai, Kyoto, November 15

Background Scene text detection methods before 2016 Proposals Filtering Regression • Generate candidates using hand-craft features • Text / non-text classification using CNN/Random forest • Refine locations using CNN [1] Jaderberg et al. Deep features for text spotting. ECCV, 2014. [2] Jaderberg et al. Reading text in the wild with convolutional neural networks. IJCV, 2016. [3] Huang et al. Robust scene text detection with convolution neural network induced mser trees. ECCV, 2014. [4] Zhang et al. Symmetry-based text line detection in natural scenes. CVPPR, 2015. [5] LGómez, D Karatzas. Textproposals: a text-specific selective search algorithm for word spotting in the wild. Pattern Recognition 70, 60-74 Xiang Bai, Kyoto, November 15

Background Scene text detectionmethods after 2016 Segmentation-based method[1] Proposal-based method[2] Hybrid method[3] [1] Zhang Z, et al. Multi-oriented text detection with fully convolutional networks. CVPR, 2016. [2] Gupta A, et al. Synthetic data for text localisation in natural images. CVPR, 2016. [3] He W, et al. Deep Direct Regression for Multi-Oriented Scene Text Detection. ICCV, 2017 [4] Liao et al. TextBoxes: A fast text detector with a single deep neural network. AAAI, 2017. Xiang Bai, Kyoto, November 15

Background Scene text recognition methods Word Classifier #words apple ball coffee . . . yellow zoo ( ) Char Classifier . . . . . . a f y z Sequence feature Extractor RNN + CTC Word/Char Level[1] l Multi-class classification with one class per word/char Sequence Level[2][3][4] l Text is a sequence of chars l The whole sequence is recognized - a - n n d - “and” [1] M. Jaderberg et al. Reading text in the wild with convolutional neural networks. IJCV, 2016. [2] B. Su et al. Accurate scene text recognition based on recurrent neural network. ACCV, 2014. [3] He et al. Reading Scene Text in Deep Convolutional Sequences. AAAI, 2016. [4] Shi B et al. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. TPAMI, 2017. Xiang Bai, Kyoto, November 15

Background Recent Trend Statistics of related papers published in 2017 top conferences Conference Detection Recognition End-to-end recognition AAAI-17 IJCAI-17 NIPS-17 ICCV-17 CVPR-17 ICDAR-17 TOTAL 0 0 0 5 3 8 16 0 1 1 1 0 2 5 2 0 0 2 0 1 5 p Over 80% text detection papers focus on multi-oriented text detection . p Scene text recognition and end-to-end recognition are paid less attention to. p Most papers focus on English text. Xiang Bai, Kyoto, November 15

分享到：

赞收藏

资料库

白翔 ICDAR2017 OCR 讲座分享.pdf

相关推荐

人工智能

热门标签

最新资料