Log In Sign Up

Arbitrary-Shaped Text Detection withAdaptive Text Region Representation

by   Xiufeng Jiang, et al.

Text detection/localization, as an important task in computer vision, has witnessed substantialadvancements in methodology and performance with convolutional neural networks. However, the vastmajority of popular methods use rectangles or quadrangles to describe text regions. These representationshave inherent drawbacks, especially relating to dense adjacent text and loose regional text boundaries,which usually cause difficulty detecting arbitrarily shaped text. In this paper, we propose a novel text regionrepresentation method, with a robust pipeline, which can precisely detect dense adjacent text instances witharbitrary shapes. We consider a text instance to be composed of an adaptive central text region mask anda corresponding expanding ratio between the central text region and the full text region. More specifically,our pipeline generates adaptive central text regions and corresponding expanding ratios with a proposedtraining strategy, followed by a new proposed post-processing algorithm which expands central text regionsto the complete text instance with the corresponding expanding ratios. We demonstrated that our new textregion representation is effective, and that the pipeline can precisely detect closely adjacent text instances ofarbitrary shapes. Experimental results on common datasets demonstrate superior performance o


page 2

page 5

page 6

page 7

page 8

page 11

page 12

page 13


Fourier Contour Embedding for Arbitrary-Shaped Text Detection

One of the main challenges for arbitrary-shaped text detection is to des...

Bidirectional Regression for Arbitrary-Shaped Text Detection

Arbitrary-shaped text detection has recently attracted increasing intere...

ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting

End-to-end text-spotting, which aims to integrate detection and recognit...

Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection

Due to the large success in object detection and instance segmentation, ...

Towards Robust Curve Text Detection with Conditional Spatial Expansion

It is challenging to detect curve texts due to their irregular shapes an...

TextField: Learning A Deep Direction Field for Irregular Scene Text Detection

Scene text detection is an important step of scene text reading system. ...

Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection

Segmentation-based methods are widely used for scene text detection due ...