Learning a classifier with very few examples: knowledg based and analogy generation of new exemples for character recognition.

Sabri Bayoudh (1) , Harold Mouch?e (2) , Laurent Miclet (1) , Eric Anquetil (2)

1 CORDIAL - Human-machine spoken dialogue
2 IMADOC - Interprétation et Reconnaissance d’Images et de Documents

This paper is basically concerned with a practical problem: the on-the-fly quick learning of handwritten character recognition systems. More generally, it explores the problem of generating new learning examples, especially from very scarce (2 to 5 per class) original learning data. It presents two different methods. The first one is based on applying distortions on original characters using knowledge on handwriting properties like speed, curvature etc. The second one consists in generation based on the notion of analogical dissimilarity which quantifies the analogical relation “A is to B almost as C is to D”. We give an algorithm to compute the k-least dissimilar objects D, hence generating k new objects from three examples A, B and C. Finally, we experimentally prove on 12 writers the efficiency of both methods, especially when used in conjunction.

Mots clés: instance generation; sequence generation by analogy; knowledge- based generation; handwritten character recognition; handwritten character recognition.

Domaines: Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]

Sabri Bayoudh, Harold Mouch?e, Laurent Miclet, Eric Anquetil. Learning a classifier with very few examples: knowledg based and analogy generation of new exemples for character recognition.. European Conference on Machine Learning, Sep 2007, Warsaw, Poland. ⟨10.1007/978-3-540-74958-5_49⟩. ⟨inria-00300717⟩