Computational Intelligence, SS08
2 VO 442.070 + 1 RU 708.070 last updated:
Course Notes (Skriptum)
Online Tutorials
Introduction to Matlab
Neural Network Toolbox
OCR with ANNs
Adaptive Filters
VC dimension
Gaussian Statistics
PCA, ICA, Blind Source Separation
Hidden Markov Models
Mixtures of Gaussians
Automatic Speech Recognition
Practical Course Slides
Animated Algorithms
Interactive Tests
Key Definitions
Literature and Links

Optical Character Recognition

A Tutorial for the Course Computational Intelligence


This tutorial demonstrates how character recognition can be done with a backpropagation network and shows how to implement this using the Matlab Neural Network toolbox. This is a slightly modified version of the character recognition application of the Matlab Neural Network toolbox (chapter 11).


This tutorial is also available as printable PDF file.

The matlab code for this tutorial is part of the Neural Network Toolbox which is installed at all PCs in the student PC rooms. To start the tutorial just type appcr1 at the matlab prompt. To get the offline HTML version of this tutorial and the matlab code as presented in the exercise course you have

  1. to download the file
  2. Unzip which will generate a subdirectory named nn-ocr.
  3. Add the path nn-ocr to the matlab search path with a command like


    if you are using a Windows machine or


    if you are using a Unix/Linux machine.