Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks (2018-12-31T00:00:00.000000Z)

TL;DR

The proposed architecture is a fully convolutional network without any recurrent connections trained with the CTC loss function, which operates on arbitrary input sizes and produces strings of arbitrary length in a very efficient and parallelizable manner.

Authors

Mohamed Yousef

2 papers

K. Hussain

1 papers

U. S. Mohammed

1 papers

TL;DR

Authors

References102 items

Visual Attention

Reseña de READ: Recognition and Enrichment of Archival Documents

ASTER: An Attentional Scene Text Recognizer with Flexible Rectification

AutoAugment: Learning Augmentation Strategies From Data

Reading scene text with fully convolutional sequence modeling

Scene Text Recognition from Two-Dimensional Perspective

How many labeled license plates are needed?

ICFHR2018 Competition on Automated Text Recognition on a READ Dataset

Improving CNN-RNN Hybrid Networks for Handwriting Recognition

Boosting the Deep Multidimensional Long-Short-Term Memory Network for Handwritten Recognition Systems

An Efficient End-to-End Neural Model for Handwritten Text Recognition

AutoAugment: Learning Augmentation Policies from Data

Handwriting Recognition of Historical Documents with Few Labeled Data

Attention U-Net: Learning Where to Look for the Pancreas

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs

Sequence Modeling with CTC

Are Multidimensional Recurrent Layers Really Necessary for Handwritten Text Recognition?

KHATT: A Deep Learning Benchmark on Arabic Script

High Performance Text Recognition Using a Hybrid Convolutional-LSTM Implementation

Data Augmentation for Recognition of Handwritten Words and Lines Using a CNN-LSTM Network

Handwritten Chinese Text Recognition Using Separable Multi-Dimensional Recurrent Neural Network

Reading Scene Text with Attention Convolutional Sequence Modeling

Scene Text Recognition with Sliding Convolutional Character Models

Squeeze-and-Excitation Networks

Augmentor: An Image Augmentation Library for Machine Learning

Depthwise Separable Convolutions for Neural Machine Translation

Self-Normalizing Neural Networks

Improving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models

Residual Attention Network for Image Classification

Attention-Based Extraction of Structured Information from Street View Imagery

Enriched Deep Recurrent Visual Attention Model for Multiple Object Recognition

Residual Convolutional CTC Networks for Automatic Speech Recognition

Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models

Highway and Residual Networks learn Unrolled Iterative Estimation

Chinese Image Text Recognition with BLSTM-CTC: A Segmentation-Free Method

Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition

Xception: Deep Learning with Depthwise Separable Convolutions

Handwriting Recognition with Large Multidimensional Long Short-Term Memory Recurrent Neural Networks

Deep LSTM Networks for Online Chinese Handwriting Recognition

Generating Synthetic Data for Text Recognition

Layer Normalization

Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention

Exploring multidimensional lstms for large vocabulary ASR

Recursive Recurrent Nets with Attention Modeling for OCR in the Wild

Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs

Deep Residual Learning for Image Recognition

Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)

Character-Aware Neural Language Models

Training Very Deep Networks

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

Grid Long Short-Term Memory

Text Detection and Recognition in Imagery: A Survey

Scene text detection and recognition: recent advances and future trends

On the Modification of Binarization Algorithms to Retain Grayscale Information for Handwritten Text Recognition

Recurrent convolutional neural network for object recognition

Spatial Transformer Networks

Deep Neural Networks for Large Vocabulary Handwritten Text Recognition

Highway Networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Adam: A Method for Stochastic Optimization

Reading Text in the Wild with Convolutional Neural Networks

Efficient object localization using Convolutional Networks

Fully convolutional networks for semantic segmentation

Accurate Scene Text Recognition Based on Recurrent Neural Network

Sequence to Sequence Learning with Neural Networks

Neural Machine Translation by Jointly Learning to Align and Translate

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

The A2iA Arabic Handwritten Text Recognition System at the Open HaRT2013 Evaluation

KHATT: An open Arabic offline handwritten text database

Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

Network In Network

Dropout Improves Recurrent Neural Networks for Handwriting Recognition

High-Performance OCR for Printed English and Fraktur Using LSTM Networks

Application-Oriented License Plate Recognition

ImageNet classification with deep convolutional neural networks

Multi-column deep neural networks for image classification