A Global Online Handwriting Recognition Approach Based on Frequent Patterns

• Main Authors: C. Gmati, H. Amiri
• Format: Article
• Language: English
• Published: D. G. Pylarinos 2018-06-01
• Series: Engineering, Technology & Applied Science Research
• Subjects: frequent features; mining frequent patterns; spatio-temporal relations; minimum threshold; online handwriting recognition
• Online Access: http://etasr.com/index.php/ETASR/article/view/1784

In this article, the handwriting signals are represented based on geometric and spatio-temporal characteristics to increase the feature vectors relevance of each object. The main goal was to extract features in the form of a numeric vector based on the extraction of frequent patterns. We used two types of frequent motifs (closed frequent patterns and maximal frequent patterns) that can represent handwritten characters pertinently. These common features patterns are generated from a raw data transformation method to achieve high relevance. A database of words consisting of two different letters was created. The proposed application gives promising results and highlights the advantages that frequent pattern extraction algorithms can achieve, as well as the central role played by the “minimum threshold” parameter in the overall description of the characters.