mfeat-pixel

**Author**: Robert P.W. Duin, Department of Applied Physics, Delft University of Technology
**Source**: [UCI](https://archive.ics.uci.edu/ml/datasets/Multiple+Features) - 1998
**Please cite**: [UCI](https://archive.ics.uci.edu/ml/citation_policy.html)

**Multiple Features Dataset: Pixel**
One of a set of 6 datasets describing features of handwritten numerals (0 - 9) extracted from a collection of Dutch utility maps. The maps were scanned in 8 bit grey value at density of 400dpi, scanned, sharpened, and thresholded. Corresponding patterns in different datasets correspond to the same original character. 200 instances per class (for a total of 2,000 instances) have been digitized in binary images.

Using this dataset, sampled versions of the original images may be obtained (15 x 16 pixels).

### Attribute Information
The mfeatures represent 240 (15 x 16) pixel averages in 2 x 3 windows.

### Relevant Papers
A slightly different version of the database is used in
M. van Breukelen, R.P.W. Duin, D.M.J. Tax, and J.E. den Hartog, Handwritten digit recognition by combined classifiers, Kybernetika, vol. 34, no. 4, 1998, 381-386.

The database as is is used in:
A.K. Jain, R.P.W. Duin, J. Mao, Statistical Pattern Recognition: A Review, IEEE Transactions on Pattern Analysis and Machine Intelligence archive, Volume 22 Issue 1, January 2000