# DanburyAI: June 2018 Workshop Competition
## 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 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. 

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

Here is a selection of what the individual training images look like: 
![enter image description here][1]

## Source
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][2])

Web source: [http://ufldl.stanford.edu/housenumbers/][3]


  [1]: http://ufldl.stanford.edu/housenumbers/32x32eg.png
  [2]: http://ufldl.stanford.edu/housenumbers/nips2011_housenumbers.pdf
  [3]: http://ufldl.stanford.edu/housenumbers/