Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence 2018
DOI: 10.24963/ijcai.2018/149
|View full text |Cite
|
Sign up to set email alerts
|

IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection

Abstract: Incidental scene text detection, especially for multioriented text regions, is one of the most challenging tasks in many computer vision applications. Different from the common object detection task, scene text often suffers from a large variance of aspect ratio, scale, and orientation. To solve this problem, we propose a novel end-to-end scene text detector IncepText from an instance-aware segmentation perspective. We design a novel Inception-Text module and introduce deformable PSROI pooling to deal with mul… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
39
0
2

Year Published

2019
2019
2021
2021

Publication Types

Select...
4
4
1

Relationship

0
9

Authors

Journals

citations
Cited by 102 publications
(41 citation statements)
references
References 5 publications
0
39
0
2
Order By: Relevance
“…It can better model the deformation at instance level compared to regular RoI warping [14,24,25]. The STN and deformable modules are widely used for recognition in the field of scene text and aerial images [29][30][31][32][33]. As for object detection in aerial images, there are more rotation and scale variations, but hardly nonrigid deformation.…”
Section: Oriented Bounding Box Regressionmentioning
confidence: 99%
“…It can better model the deformation at instance level compared to regular RoI warping [14,24,25]. The STN and deformable modules are widely used for recognition in the field of scene text and aerial images [29][30][31][32][33]. As for object detection in aerial images, there are more rotation and scale variations, but hardly nonrigid deformation.…”
Section: Oriented Bounding Box Regressionmentioning
confidence: 99%
“…Recall Precision Hmean EAST [34] 67.4 87.3 76.1 SegLink [24] 70.0 86.0 77.0 PixelLink [3] 73.2 83.0 77.8 TextSnake [19] 73.9 83.2 78.3 InceptText [28] 79.0 87.5 83.0 MCN [18] 79.0 88.0 83.0 Proposed 82.1 85.2 83.6 Table 8. Results on MSRA-TD500.…”
Section: Methodsmentioning
confidence: 99%
“…One-stage methods including Deep Direct Regression [5], TextBox [12], TextBoxes++ [11], DMPNet [16], SegLink [24] and EAST [34], directly estimate bounding boxes of text regions in one step. Two-stage methods in-clude R2CNN [8], RRD [13], RRPN [22], IncepText [28] and FEN [31]. They consist of text proposal generation stage, in which candidate text regions are generated, and bounding box refinement stage, in which candidate text regions are verified and refined to generate the final detection result.…”
Section: Related Workmentioning
confidence: 99%
“…The key of text detection is designing features to distinguish text from backgrounds. Recently, Convolutional Neural Networks (CNN) based methods such as EAST [1] and IncepText [4] have achieved the state-of-the-art performance for text detection. Like other computer vision tasks, deeper networks provide better performances.…”
Section: Introductionmentioning
confidence: 99%