IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
Not on the map. Why?
Abstract (arXiv)
Incidental scene text detection, especially for multi-oriented 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 multi-oriented text detection. Extensive experiments on ICDAR2015, RCTW-17, and MSRA-TD500 datasets demonstrate our method's superiority in terms of both effectiveness and efficiency. Our proposed method achieves 1st place result on ICDAR2015 challenge and the state-of-the-art performance on other datasets. Moreover, we have released our implementation as an OCR product which is available for public access.
Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 May 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 6; 2022: 4; 2023: 2.
12 papers.
- 2022MMRotate: A Rotated Object Detection Benchmark using PyTorchcited by 115
- 2021TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representationcited by 26
- 2022Kernel Proposal Network for Arbitrary Shape Text Detectioncited by 17
- 2021Industrial Scene Text Detection with Refined Feature-attentive Networkcited by 16
- 2022Arbitrary Shape Text Detection via Segmentation with Probability Mapscited by 15
- 2021I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detectioncited by 14
- 2023Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learningcited by 12
- 2022Graph Fusion Network for Multi-Oriented Object Detectioncited by 7
- 2021Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Linkscited by 5
- 2021One-shot Key Information Extraction from Document with Deep Partial Graph Matchingcited by 3
- 2021A DCNN-based Arbitrarily-Oriented Object Detector for Quality Control and Inspection Applicationcited by 0
- 2023Towards Detecting, Recognizing, and Parsing the Address Information from Bangla Signboard: A Deep Learning-based Approachcited by 0
- 2023Towards Detecting, Recognizing, and Parsing the Address Information from Bangla Signboard: A Deep Learning-based Approach22 Nov 2023
- 2023Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning14 Aug 2023
- 2022Arbitrary Shape Text Detection via Segmentation with Probability Maps26 Aug 2022
- 2022Graph Fusion Network for Multi-Oriented Object Detection7 May 2022
- 2022MMRotate: A Rotated Object Detection Benchmark using PyTorch28 Apr 2022
- 2022Kernel Proposal Network for Arbitrary Shape Text Detection12 Mar 2022
- 2021TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation25 Oct 2021
- 2021Industrial Scene Text Detection with Refined Feature-attentive Network25 Oct 2021
- 2021One-shot Key Information Extraction from Document with Deep Partial Graph Matching26 Sep 2021
- 2021I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection3 Aug 2021
- 2021Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links1 Mar 2021
- 2021A DCNN-based Arbitrarily-Oriented Object Detector for Quality Control and Inspection Application19 Jan 2021