X80

Handwritten character dataset, 45 objects with 8 features in 3 classes

   A = X80

Description

Load the dataset in A. This is the 80X dataset, having 3 classes.  The 8 features are the distances from a bounding box to the  pixels of a set of handwritten characters 'X', '8' and '0', measured from  the corners along the diagonals and from the edge midpoints along the  horizontal and vertical central axes.

Reference(s)

1. R. Dubes and A.K. Jain, Clustering techniques: The user's dilemma, Pattern Recognition, Volume 8, Issue 4, October 1976, Pages 247-260.
2. A.K. Jain, R.C. Dubes, C.C. Chen, Bootstrap Techniques for Error Estimation IEEE Trans. Pattern Anal. and Mach. Intel., 9(5), pp. 628-633, 1987.

See also