Arbitrary-Shaped Text Detection withAdaptive Text Region Representation

TL;DR

This paper introduces a novel adaptive text region representation method that enables precise detection of arbitrarily shaped and densely packed text instances in images, overcoming limitations of traditional rectangular approaches.

Contribution

The paper proposes a new text region representation and detection pipeline that accurately detects dense, arbitrarily shaped text regions using adaptive central masks and expansion ratios.

Findings

Effective detection of arbitrarily shaped text instances.

Superior performance on standard datasets.

Precise detection of closely adjacent text.

Abstract

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