Handwritten Digit Recognition using Edit Distance-Based KNN

Abstract : We discuss the student project given for the last 5 years to the 1st year Master Students which follow the Machine Learning lecture at the University Jean Monnet in Saint Etienne, France. The goal of this project is to develop a GUI that can recognize digits and/or letters drawn manually. The system is based on a string representation of the dig- its using Freeman codes and on the use of an edit-distance-based K-Nearest Neighbors classifier. In addition to the machine learning knowledge about the KNN classifier (and its optimizations to make it efficient) and about the edit distance, some programming skills on how to develop such a GUI are required.
Document type :
Conference papers
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download

Contributor : Elisa Fromont <>
Submitted on : Wednesday, July 4, 2012 - 6:30:02 PM
Last modification on : Wednesday, July 25, 2018 - 2:05:30 PM
Long-term archiving on : Friday, October 5, 2012 - 4:48:06 AM


Files produced by the author(s)


  • HAL Id : hal-00714509, version 1



Marc Bernard, Elisa Fromont, Amaury Habrard, Marc Sebban. Handwritten Digit Recognition using Edit Distance-Based KNN. Teaching Machine Learning Workshop, Jun 2012, Edinburgh, Scotland, United Kingdom. ⟨hal-00714509⟩



Record views


Files downloads