Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
Venue
ICLR2014, ICLR2014 (to appear)
Publication Year
2014
Authors
Ian Goodfellow, Yaroslav Bulatov, Julian Ibarz, Sacha Arnoud, Vinay Shet
BibTeX
Abstract
Recognizing arbitrary multi-character text in unconstrained natural photographs is
a hard problem. In this paper, we address an equally hard sub-problem in this
domain viz. recognizing arbitrary multi-digit numbers from Street View imagery.
Traditional approaches to solve this problem typically separate out the localiza-
tion, segmentation, and recognition steps. In this paper we propose a unified ap-
proach that integrates these three steps via the use of a deep convolutional neu-
ral network that operates directly on the image pixels. We employ the DistBe- lief
(Dean et al., 2012) implementation of deep neural networks in order to train large,
distributed neural networks on high quality images. We find that the per- formance
of this approach increases with the depth of the convolutional network, with the
best performance occurring in the deepest architecture we trained, with eleven
hidden layers. We evaluate this approach on the publicly available SVHN dataset and
achieve over 96% accuracy in recognizing complete street numbers. We show that on a
per-digit recognition task, we improve upon the state-of-the-art and achieve 97.84%
accuracy. We also evaluate this approach on an even more challenging dataset
generated from Street View imagery containing several tens of millions of street
number annotations and achieve over 90% accuracy. Our evaluations further indicate
that at specific operating thresholds, the performance of the proposed system is
comparable to that of human operators. To date, our system has helped us extract
close to 100 million physical street numbers from Street View imagery worldwide.
