Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition

06/09/2014
by   Max Jaderberg, et al.
0

In this work we present a framework for the recognition of natural scene text. Our framework does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past. The deep neural network models at the centre of this framework are trained solely on data produced by a synthetic text generation engine -- synthetic data that is highly realistic and sufficient to replace real data, giving us infinite amounts of training data. This excess of data exposes new possibilities for word recognition models, and here we consider three models, each one "reading" words in a different way: via 90k-way dictionary encoding, character sequence encoding, and bag-of-N-grams encoding. In the scenarios of language based and completely unconstrained text recognition we greatly improve upon state-of-the-art performance on standard datasets, using our fast, simple machinery and requiring zero data-acquisition costs.

READ FULL TEXT
research
12/04/2014

Reading Text in the Wild with Convolutional Neural Networks

In this work we present an end-to-end system for text spotting -- locali...
research
04/17/2018

Synthetic data generation for Indic handwritten text recognition

This paper presents a novel approach to generate synthetic dataset for h...
research
06/30/2020

Using Human Psychophysics to Evaluate Generalization in Scene Text Recognition Models

Scene text recognition models have advanced greatly in recent years. Ins...
research
09/28/2022

Synthesizing Annotated Image and Video Data Using a Rendering-Based Pipeline for Improved License Plate Recognition

An insufficient number of training samples is a common problem in neural...
research
04/26/2013

Reading Ancient Coin Legends: Object Recognition vs. OCR

Standard OCR is a well-researched topic of computer vision and can be co...
research
02/27/2017

DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition

Recent progress in computer vision has been dominated by deep neural net...
research
10/27/2020

Improving Text Relationship Modeling with Artificial Data

Data augmentation uses artificially-created examples to support supervis...

Please sign up or login with your details

Forgot password? Click here to reset