Program5 - Neural Networks, CAP 6615 Program 5, Due 20...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Neural Networks, CAP 6615 Program 5, Due 20 April 2011 In this assignment, you'll perform handwritten character classification. The underlying data are drawn from the CEDAR dataset which was prepared for the U.S. Postal service using images of actual handwritten addresses from envelopes. More information about this dataset is available from http://www.cedar.buffalo.edu/Databases/CDROM1 . I have extracted images from this dataset and placed them in several files available to you, namely, http://www.cise.ufl.edu/~jnw/CAP6615sp11/Resources/train_upper.7z which is a 7zip file containing 9,119 PBM images of uppercase handwritten letters in a directory called train_upper http://www.cise.ufl.edu/~jnw/CAP6615sp11/Resources/test_upper.7z which contains 1,042 PBM images of uppercase handwritten letters in directory test_upper As the names of these files may suggest, you are to use the characters in train_upper and test on the characters in test_upper. More specific details will be provided below. To make your job easier, you don't have to determine what features to use for this task if you don't want
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 2

Program5 - Neural Networks, CAP 6615 Program 5, Due 20...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online