Scene Text Recognition

144 papers with code • 15 benchmarks • 29 datasets

See Scene Text Detection for leaderboards in this task.

Libraries

Use these libraries to find Scene Text Recognition models and implementations

Most implemented papers

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

PaddlePaddle/PaddleOCR 21 Jul 2015

In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence recognition.

What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis

clovaai/deep-text-recognition-benchmark ICCV 2019

Many new proposals for scene text recognition (STR) models have been introduced in recent years.

Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition

PaddlePaddle/PaddleOCR 2 Nov 2018

Recognizing irregular text in natural scene images is challenging due to the large variance in text appearance, such as curvature, orientation and distortion.

TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models

microsoft/unilm 21 Sep 2021

Text recognition is a long-standing research problem for document digitalization.

FOTS: Fast Oriented Text Spotting with a Unified Network

jiangxiluning/FOTS.PyTorch CVPR 2018

Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community.

A Multi-Object Rectified Attention Network for Scene Text Recognition

Canjie-Luo/MORAN_v2 10 Jan 2019

It decreases the difficulty of recognition and enables the attention-based sequence recognition network to more easily read irregular text.

MASTER: Multi-Aspect Non-local Network for Scene Text Recognition

wenwenyu/MASTER-pytorch 7 Oct 2019

Attention-based scene text recognizers have gained huge success, which leverages a more compact intermediate representation to learn 1d- or 2d- attention by a RNN-based encoder-decoder architecture.

Robust Scene Text Recognition with Automatic Rectification

PaddlePaddle/PaddleOCR CVPR 2016

We show that the model is able to recognize several types of irregular text, including perspective text and curved text.

Decoupled Attention Network for Text Recognition

Canjie-Luo/Scene-Text-Image-Transformer 21 Dec 2019

To remedy this issue, we propose a decoupled attention network (DAN), which decouples the alignment operation from using historical decoding results.

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

open-mmlab/mmocr ECCV 2020

Theoretically, our proposed method, dubbed \emph{RobustScanner}, decodes individual characters with dynamic ratio between context and positional clues, and utilizes more positional ones when the decoding sequences with scarce context, and thus is robust and practical.