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

TL;DR

IncepText introduces a novel end-to-end scene text detection method that effectively handles multi-oriented text regions using a new Inception-Text module and deformable PSROI pooling, achieving top performance on multiple datasets.

Contribution

The paper presents a new Inception-Text module and deformable PSROI pooling for improved multi-oriented scene text detection, outperforming existing methods.

Findings

Achieved 1st place on ICDAR2015 challenge

Set new state-of-the-art results on RCTW-17 and MSRA-TD500 datasets

Demonstrated effectiveness and efficiency of the proposed method

Abstract

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.