About

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Datasets

Greatest papers with code

Robust Scene Text Recognition with Automatic Rectification

CVPR 2016 PaddlePaddle/PaddleOCR

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

RECTIFICATION SCENE TEXT SCENE TEXT RECOGNITION

FReLU: Flexible Rectified Linear Units for Improving Convolutional Neural Networks

25 Jun 2017ducha-aiki/caffenet-benchmark

Rectified linear unit (ReLU) is a widely used activation function for deep convolutional neural networks.

IMAGE CLASSIFICATION RECTIFICATION

ASTER: An Attentional Scene Text Recognizer with Flexible Rectification

good 2018 bgshih/aster

SCENE text recognition has attracted great interest from the academia and the industry in recent years owing to its importance in a wide range of applications.

OPTICAL CHARACTER RECOGNITION RECTIFICATION SCENE TEXT SCENE TEXT RECOGNITION

A Multi-Object Rectified Attention Network for Scene Text Recognition

10 Jan 2019Canjie-Luo/MORAN_v2

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

RECTIFICATION SCENE TEXT SCENE TEXT RECOGNITION

Generic 3D Representation via Pose Estimation and Matching

23 Oct 2017amir32002/3D_Street_View

Though a large body of computer vision research has investigated developing generic semantic representations, efforts towards developing a similar representation for 3D has been limited.

POSE ESTIMATION RECTIFICATION

Rethinking Irregular Scene Text Recognition

30 Aug 2019Jyouhou/ICDAR2019-ArT-Recognition-Alchemy

Reading text from natural images is challenging due to the great variety in text font, color, size, complex background and etc..

RECTIFICATION SCENE TEXT SCENE TEXT DETECTION

Document Rectification and Illumination Correction using a Patch-based CNN

20 Sep 2019xiaoyu258/DocProj

We propose a novel learning method to rectify document images with various distortion types from a single input image.

OPTICAL CHARACTER RECOGNITION RECTIFICATION

WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving

ICCV 2019 valeoai/WoodScape

Fisheye cameras are commonly employed for obtaining a large field of view in surveillance, augmented reality and in particular automotive applications.

AUTONOMOUS DRIVING DEPTH ESTIMATION RECTIFICATION

KISS: Keeping It Simple for Scene Text Recognition

19 Nov 2019Bartzi/kiss

Most of these methods propose novel building blocks for neural networks.

RECTIFICATION SCENE TEXT SCENE TEXT RECOGNITION