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

arXiv: https://arxiv.org/abs/1805.01167 · HTML: https://mlsanity.com/paper/1805.01167/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2018.

## Built on by (most cited first, 12 of 12)

- [MMRotate: A Rotated Object Detection Benchmark using PyTorch](https://mlsanity.com/paper/2204.13317/) (2022)
- [TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation](https://mlsanity.com/paper/2110.12826/) (2021)
- [Kernel Proposal Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2203.06410/) (2022)
- [Industrial Scene Text Detection with Refined Feature-attentive Network](https://mlsanity.com/paper/2110.12663/) (2021)
- [Arbitrary Shape Text Detection via Segmentation with Probability Maps](https://mlsanity.com/paper/2208.12419/) (2022)
- [I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection](https://mlsanity.com/paper/2108.01343/) (2021)
- [Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning](https://mlsanity.com/paper/2308.07202/) (2023)
- [Graph Fusion Network for Multi-Oriented Object Detection](https://mlsanity.com/paper/2205.03562/) (2022)
- [Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links](https://mlsanity.com/paper/2103.00785/) (2021)
- [One-shot Key Information Extraction from Document with Deep Partial Graph Matching](https://mlsanity.com/paper/2109.13967/) (2021)
- [A DCNN-based Arbitrarily-Oriented Object Detector for Quality Control and Inspection Application](https://mlsanity.com/paper/2101.07383/) (2021)
- [Towards Detecting, Recognizing, and Parsing the Address Information from Bangla Signboard: A Deep Learning-based Approach](https://mlsanity.com/paper/2311.13222/) (2023)

## 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.