Convolutional Neural Networks Applied to House Numbers Digit Classification

Details Convolutional Neural Networks Applied to House Numbers Digit Classification Convolutional Neural Networks Applied to House Numbers Digit Classification

2012-04-18

arxiv.org/abs/1204.3968v1

Computer Science

Computer Vision and Pattern Recognition

4 pages, 6 figures, 2 tables

Scientific paper

We classify digits of real-world house numbers using convolutional neural networks (ConvNets). ConvNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 94.85% accuracy on the SVHN dataset (45.2% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net.

Affiliated with

Also associated with

No associations

Rating

Convolutional Neural Networks Applied to House Numbers Digit Classification does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Convolutional Neural Networks Applied to House Numbers Digit Classification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Convolutional Neural Networks Applied to House Numbers Digit Classification will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-410986