Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting

02/17/2020
by   Liang Qiao, et al.
12

Many approaches have recently been proposed to detect irregular scene text and achieved promising results. However, their localization results may not well satisfy the following text recognition part mainly because of two reasons: 1) recognizing arbitrary shaped text is still a challenging task, and 2) prevalent non-trainable pipeline strategies between text detection and text recognition will lead to suboptimal performances. To handle this incompatibility problem, in this paper we propose an end-to-end trainable text spotting approach named Text Perceptron. Concretely, Text Perceptron first employs an efficient segmentation-based text detector that learns the latent text reading order and boundary information. Then a novel Shape Transform Module (abbr. STM) is designed to transform the detected feature regions into regular morphologies without extra parameters. It unites text detection and the following recognition part into a whole framework, and helps the whole network achieve global optimization. Experiments show that our method achieves competitive performance on two standard text benchmarks, i.e., ICDAR 2013 and ICDAR 2015, and also obviously outperforms existing methods on irregular text benchmarks SCUT-CTW1500 and Total-Text.

READ FULL TEXT

page 1

page 4

page 7

page 8

research
08/24/2019

Towards Unconstrained End-to-End Text Spotting

We propose an end-to-end trainable network that can simultaneously detec...
research
09/20/2023

Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text

Recently, Transformer-based text detection techniques have sought to pre...
research
12/08/2020

MANGO: A Mask Attention Guided One-Stage Scene Text Spotter

Recently end-to-end scene text spotting has become a popular research to...
research
03/10/2022

DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting

Recent end-to-end scene text spotters have achieved great improvement in...
research
12/24/2018

TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network

Reading text from images remains challenging due to multi-orientation, p...
research
08/06/2019

Symmetry-constrained Rectification Network for Scene Text Recognition

Reading text in the wild is a very challenging task due to the diversity...
research
10/20/2021

ARTS: Eliminating Inconsistency between Text Detection and Recognition with Auto-Rectification Text Spotter

Recent approaches for end-to-end text spotting have achieved promising r...

Please sign up or login with your details

Forgot password? Click here to reset