Digit_classifier

Image classifier for the SVHN dataset

A neural network project that classifies real-world images digits.

Dataset

• 10 classes, 1 for each digit. Digit '1' has label 1, '9' has label 9 and '0' has label 10.
• 73257 digits for training, 26032 digits for testing, and 531131 additional, somewhat less difficult samples, to use as extra training data
• Comes in two formats:

1. Original images with character level bounding boxes.
2. MNIST-like 32-by-32 images centered around a single character (many of the images do contain some distractors at the sides).

Dataset Sample

Source

The Street View House Numbers (SVHN) Dataset

Reference

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)