Unconstrained text recognition is an important computer vision task,
featuring a wide variety of different sub-tasks, each with its own set of
challenges. One of the biggest promises of deep neural networks has been the
convergence and automation of feature extractors from input raw signals,
allowing for the highest possible performance with minimum required domain
knowledge. To this end, we propose a data-efficient, end-to-end neural network
model for generic, unconstrained text recognition. In our proposed architecture
we strive for simplicity and efficiency without sacrificing recognition
accuracy. Our proposed architecture is a fully convolutional network without
any recurrent connections trained with the CTC loss function. Thus it operates
on arbitrary input sizes and produces strings of arbitrary length in a very
efficient and parallelizable manner. We show the generality and superiority of
our proposed text recognition architecture by achieving state of the art
results on seven public benchmark datasets, covering a wide spectrum of text
recognition tasks, namely: Handwriting Recognition, CAPTCHA recognition, OCR,
License Plate Recognition, and Scene Text Recognition. Our proposed
architecture has won the ICFHR2018 Competition on Automated Text Recognition on
a READ Dataset.
%0 Generic
%1 citeulike:14689029
%A xxx,
%D 2018
%K arch ocr regularization
%T Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks
%U http://arxiv.org/abs/1812.11894
%X Unconstrained text recognition is an important computer vision task,
featuring a wide variety of different sub-tasks, each with its own set of
challenges. One of the biggest promises of deep neural networks has been the
convergence and automation of feature extractors from input raw signals,
allowing for the highest possible performance with minimum required domain
knowledge. To this end, we propose a data-efficient, end-to-end neural network
model for generic, unconstrained text recognition. In our proposed architecture
we strive for simplicity and efficiency without sacrificing recognition
accuracy. Our proposed architecture is a fully convolutional network without
any recurrent connections trained with the CTC loss function. Thus it operates
on arbitrary input sizes and produces strings of arbitrary length in a very
efficient and parallelizable manner. We show the generality and superiority of
our proposed text recognition architecture by achieving state of the art
results on seven public benchmark datasets, covering a wide spectrum of text
recognition tasks, namely: Handwriting Recognition, CAPTCHA recognition, OCR,
License Plate Recognition, and Scene Text Recognition. Our proposed
architecture has won the ICFHR2018 Competition on Automated Text Recognition on
a READ Dataset.
@misc{citeulike:14689029,
abstract = {{ Unconstrained text recognition is an important computer vision task,
featuring a wide variety of different sub-tasks, each with its own set of
challenges. One of the biggest promises of deep neural networks has been the
convergence and automation of feature extractors from input raw signals,
allowing for the highest possible performance with minimum required domain
knowledge. To this end, we propose a data-efficient, end-to-end neural network
model for generic, unconstrained text recognition. In our proposed architecture
we strive for simplicity and efficiency without sacrificing recognition
accuracy. Our proposed architecture is a fully convolutional network without
any recurrent connections trained with the CTC loss function. Thus it operates
on arbitrary input sizes and produces strings of arbitrary length in a very
efficient and parallelizable manner. We show the generality and superiority of
our proposed text recognition architecture by achieving state of the art
results on seven public benchmark datasets, covering a wide spectrum of text
recognition tasks, namely: Handwriting Recognition, CAPTCHA recognition, OCR,
License Plate Recognition, and Scene Text Recognition. Our proposed
architecture has won the ICFHR2018 Competition on Automated Text Recognition on
a READ Dataset.}},
added-at = {2019-02-27T22:23:29.000+0100},
archiveprefix = {arXiv},
author = {xxx},
biburl = {https://www.bibsonomy.org/bibtex/28dce947b99065455290d935e259d827f/nmatsuk},
citeulike-article-id = {14689029},
citeulike-linkout-0 = {http://arxiv.org/abs/1812.11894},
citeulike-linkout-1 = {http://arxiv.org/pdf/1812.11894},
day = 31,
eprint = {1812.11894},
interhash = {65928c09ab262a878facb275634ef8c0},
intrahash = {8dce947b99065455290d935e259d827f},
keywords = {arch ocr regularization},
month = dec,
posted-at = {2019-02-12 11:22:14},
priority = {4},
timestamp = {2019-02-27T22:23:29.000+0100},
title = {{Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks}},
url = {http://arxiv.org/abs/1812.11894},
year = 2018
}