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

Yang, Qimeng; Cheng, Mengli; Zhou, Wenmeng; Chen, Yan; Qiu, Minghui; Lin, Wei

doi:10.24963/ijcai.2018/149

Cited by 102 publications

(41 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

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%

Learning RoI Transformer for Oriented Object Detection in Aerial Images

Ding

Xue

Yang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

962

661

View full text Add to dashboard Cite

Object detection in aerial images is an active yet challenging task in computer vision because of the birdview perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects. This leads to the common misalignment between the final object classification confidence and localization accuracy. Although rotated anchors have been used to tackle this problem, the design of them always multiplies the number of anchors and dramatically increases the computational complexity. In this paper, we propose a RoI Transformer to address these problems. More precisely, to improve the quality of region proposals, we first designed a Rotated RoI (RRoI) learner to transform a Horizontal Region of Interest (HRoI) into a Rotated Region of Interest (RRoI). Based on the RRoIs, we then proposed a Rotated Position Sensitive RoI Align (RPS-RoI-Align) module to extract rotation-invariant features from them for boosting subsequent classification and regression. Our RoI Transformer is with light weight and can be easily embedded into detectors for oriented object detection. A simple implementation of the RoI Transformer has achieved state-of-the-art performances on two common and challenging aerial datasets, i.e., DOTA and HRSC2016, with a neglectable reduction to detection speed. Our RoI Transformer exceeds the deformable Position Sensitive RoI pooling when oriented bounding-box annotations are available. Extensive experiments have also validated the flexibility and effectiveness of our RoI Transformer. The results demonstrate that it can be easily integrated with other detector architectures and significantly improve the performances.

show abstract

Section: Oriented Bounding Box Regressionmentioning

confidence: 99%

Learning RoI Transformer for Oriented Object Detection in Aerial Images

Ding

Xue

Yang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

962

661

View full text Add to dashboard Cite

show abstract

“…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%

Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation

Wang

Jiang

Luo

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

179

View full text Add to dashboard Cite

Scene text detection attracts much attention in computer vision, because it can be widely used in many applications such as real-time text translation, automatic information entry, blind person assistance, robot sensing and so on. Though many methods have been proposed for horizontal and oriented texts, detecting irregular shape texts such as curved texts is still a challenging problem. To solve the problem, we propose a robust scene text detection method with adaptive text region representation. Given an input image, a text region proposal network is first used for extracting text proposals. Then, these proposals are verified and refined with a refinement network. Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found. In this way, text regions of arbitrary shapes are detected and represented with adaptive number of boundary points. This gives more accurate description of text regions. Experimental results on five benchmarks, namely, CTW1500, TotalText, ICDAR2013, ICDAR2015 and MSRA-TD500, show that the proposed method achieves state-ofthe-art in scene text detection.

show abstract

“…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%

Efficient Scene Text Detection with Textual Attention Tower

Zhang

Liu

Xiao³

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Scene text detection has received attention for years and achieved an impressive performance across various benchmarks. In this work, we propose an efficient and accurate approach to detect multi-oriented text in scene images. The proposed feature fusion mechanism allows us to use a shallower network to reduce the computational complexity. A self-attention mechanism is adopted to suppress false positive detections. Experiments on public benchmarks including ICDAR 2013, ICDAR 2015 and MSRA-TD500 show that our proposed approach can achieve better or comparable performances with fewer parameters and less computational cost.

show abstract

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

Cited by 102 publications

References 5 publications

Learning RoI Transformer for Oriented Object Detection in Aerial Images

Learning RoI Transformer for Oriented Object Detection in Aerial Images

Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation

Efficient Scene Text Detection with Textual Attention Tower

Contact Info

Product

Resources

About