|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM294276793 |
| 003 |
DE-627 |
| 005 |
20231225081131.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2019 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2019.2900589
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n0980.xml
|
| 035 |
|
|
|a (DE-627)NLM294276793
|
| 035 |
|
|
|a (NLM)30802859
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Xu, Yongchao
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a TextField
|b Learning a Deep Direction Field for Irregular Scene Text Detection
|
| 264 |
|
1 |
|c 2019
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 06.09.2019
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Scene text detection is an important step in the scene text reading system. The main challenges lie in significantly varied sizes and aspect ratios, arbitrary orientations, and shapes. Driven by the recent progress in deep learning, impressive performances have been achieved for multi-oriented text detection. Yet, the performance drops dramatically in detecting the curved texts due to the limited text representation (e.g., horizontal bounding boxes, rotated rectangles, or quadrilaterals). It is of great interest to detect the curved texts, which are actually very common in natural scenes. In this paper, we present a novel text detector named TextField for detecting irregular scene texts. Specifically, we learn a direction field pointing away from the nearest text boundary to each text point. This direction field is represented by an image of 2D vectors and learned via a fully convolutional neural network. It encodes both binary text mask and direction information used to separate adjacent text instances, which is challenging for the classical segmentation-based approaches. Based on the learned direction field, we apply a simple yet effective morphological-based post-processing to achieve the final detection. The experimental results show that the proposed TextField outperforms the state-of-the-art methods by a large margin (28% and 8%) on two curved text datasets: Total-Text and SCUT-CTW1500, respectively; TextField also achieves very competitive performance on multi-oriented datasets: ICDAR 2015 and MSRA-TD500. Furthermore, TextField is robust in generalizing unseen datasets
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Wang, Yukang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhou, Wei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Yongpan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Zhibo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Bai, Xiang
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 28(2019), 11 vom: 22. Nov., Seite 5566-5579
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:28
|g year:2019
|g number:11
|g day:22
|g month:11
|g pages:5566-5579
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2019.2900589
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 28
|j 2019
|e 11
|b 22
|c 11
|h 5566-5579
|