[Lisa_teatalk] Tea talk tomorrow 13:00 (changed room to AA3256)

Razvan Pascanu r.pascanu at gmail.com
Tue Feb 25 12:44:16 EST 2014


Hi all,

 This week Ian is going to talk about his ICLR submission.
The room is going to be the main Lisa Lab (AA 3256).

Hope to see many of you there.

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


Abstract: A tea talk on this ICLR submission:
https://drive.google.com/file/d/0B64011x02sIkd3RwSDRpTXlKSzQ/edit?usp=sharing
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 localization, segmentation, and recognition
steps. In this paper we propose a unified approach that integrates these
three steps via the use of a deep convolutional neural network that
operates directly on the image pixels. We employ the DistBelief (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
performance 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.


Best,
Razvan
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_teatalk/attachments/20140225/1716c1f2/attachment.html 


More information about the Lisa_teatalk mailing list