Letter Image Recognition Data

The objective is to identify each of a large number of black-and-white rectangular pixel displays as one of the 26 capital letters in the English alphabet. The character images were based on 20 different fonts and each letter within these 20 fonts was randomly distorted to produce a file of 20,000 unique stimuli. Each stimulus was converted into 16 primitive numerical attributes (statistical moments and edge counts) which were then scaled to fit into a range of integer values from 0 through 15. We typically train on the first 16000 items and then use the resulting model to predict the letter category for the remaining 4000. See the article cited below for more details.


A data frame with 20,000 observations on 17 variables, the first is a factor with levels A-Z, the remaining 16 are numeric.

[,1] lettr
capital letter [,2]
x.box horizontal position of box
[,3] y.box
vertical position of box [,4]
width width of box
[,5] high
height of box [,6]
onpix total number of on pixels
[,7] x.bar
mean x of on pixels in box [,8]
y.bar mean y of on pixels in box
[,9] x2bar
mean x variance [,10]
y2bar mean y variance
[,11] xybar
mean x y correlation [,12]
x2ybr mean of $x^2 y$
[,13] xy2br
mean of $x y^2$ [,14]
x.ege mean edge count left to right
[,15] xegvy
correlation of x.ege with y [,16]
y.ege mean edge count bottom to top
[,17] yegvx
correlation of y.ege with x [,1]


  • Creator: David J. Slate
  • Odesta Corporation; 1890 Maple Ave; Suite 115; Evanston, IL 60201
  • Donor: David J. Slate (dave@math.nwu.edu) (708) 491-3867
These data have been taken from the UCI Repository Of Machine Learning Databases at and were converted to R format by Friedrich Leisch.


P. W. Frey and D. J. Slate (Machine Learning Vol 6/2 March 91): "Letter Recognition Using Holland-style Adaptive Classifiers".

The research for this article investigated the ability of several variations of Holland-style adaptive classifier systems to learn to correctly guess the letter categories associated with vectors of 16 integer attributes extracted from raster scan images of the letters. The best accuracy obtained was a little over 80%. It would be interesting to see how well other methods do with the same data.

Newman, D.J. & Hettich, S. & Blake, C.L. & Merz, C.J. (1998). UCI Repository of machine learning databases [http://www.ics.uci.edu/~mlearn/MLRepository.html]. Irvine, CA: University of California, Department of Information and Computer Science.

  • LetterRecognition
library(mlbench) data(LetterRecognition) summary(LetterRecognition)
Documentation reproduced from package mlbench, version 2.1-1, License: GPL-2

Community examples

Looks like there are no examples yet.