SVHN

**Author**: Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, Andrew Y. Ng
**Source**: [original](http://ufldl.stanford.edu/housenumbers/) - 2011
**Please cite**: Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, Andrew Y. Ng Reading Digits in Natural Images with Unsupervised Feature Learning NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011. [PDF](http://ufldl.stanford.edu/housenumbers/nips2011_housenumbers.pdf)

**The Street View House Numbers (SVHN) Dataset**

SVHN is a real-world image dataset for developing machine learning and object recognition algorithms with minimal requirement on data preprocessing and formatting. It can be seen as similar in flavor to MNIST (e.g., the images are of small cropped digits), but incorporates an order of magnitude more labeled data and comes from a significantly harder, unsolved, real world problem (recognizing digits and numbers in natural scene images). SVHN is obtained from house numbers in Google Street View images.

It consists of 10 classes, 1 for each digit. Digit '1' has label 1, '9' has label 9 and '0' has label 10. The data comes in a MNIST-like format of 32-by-32 RGB images centered around a single digit (many of the images do contain some distractors at the sides).