Paper: | MLSP-P7.8 | ||
Session: | Pattern Recognition and Classification II | ||
Time: | Friday, May 21, 15:30 - 17:30 | ||
Presentation: | Poster | ||
Topic: | Machine Learning for Signal Processing: Signal detection, Pattern Recognition and Classification | ||
Title: | ON-LINE CHARACTER RECOGNITION USING HISTOGRAMS OF FEATURES AND AN ASSOCIATIVE MEMORY | ||
Authors: | Neila Mezghani; INRS Telecommunications | ||
Amar Mitiche; INRS Telecommunications | |||
Mohamed Cheriet; ETS | |||
Abstract: | The purpose of this study is to investigate a new representation of shape and its use in handwritten on-line character recognition. Thi representation is based on first- and second-order statistics, namely the empirical distribution of features such as tangents, and tangent differences at distant points along the character signal. Recognition is carried out by an associative memory trained using this representation and the Hellinger distance which measures distance between distributions. We report on extensive experiments that show the pertinence of the representation and the superior performance of the scheme. | ||
Back |
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops