CVMay 3, 2018

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

arXiv:1805.01167v2116 citations
Originality Incremental advance
AI Analysis

This addresses the problem of detecting text in varied orientations and scales for computer vision applications, representing a strong incremental improvement in a specific domain.

The paper tackled multi-oriented scene text detection by proposing IncepText, an end-to-end detector using an Inception-Text module and deformable PSROI pooling, achieving state-of-the-art results including 1st place on the ICDAR2015 challenge.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes