A Global Online Handwriting Recognition Approach Based on Frequent Patterns
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 ty...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
D. G. Pylarinos
2018-06-01
|
Series: | Engineering, Technology & Applied Science Research |
Subjects: | |
Online Access: | http://etasr.com/index.php/ETASR/article/view/1784 |
id |
doaj-282fc3c7728a4702b8f0767bdc3a09f8 |
---|---|
record_format |
Article |
spelling |
doaj-282fc3c7728a4702b8f0767bdc3a09f82020-12-02T16:37:06ZengD. G. PylarinosEngineering, Technology & Applied Science Research2241-44871792-80362018-06-0183522A Global Online Handwriting Recognition Approach Based on Frequent PatternsC. Gmati0H. Amiri1LR-SITI Laboratory, National Engineering School of Tunis, El Manar University, Tunis, TunisiaTechnologies of Information Laboratory (LR-SITI), National Engineering School of Tunis (ENIT), Tunis, TunisiaIn 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. http://etasr.com/index.php/ETASR/article/view/1784frequent featuresmining frequent patternsspatio-temporal relationsminimum thresholdonline handwriting recognition |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
C. Gmati H. Amiri |
spellingShingle |
C. Gmati H. Amiri A Global Online Handwriting Recognition Approach Based on Frequent Patterns Engineering, Technology & Applied Science Research frequent features mining frequent patterns spatio-temporal relations minimum threshold online handwriting recognition |
author_facet |
C. Gmati H. Amiri |
author_sort |
C. Gmati |
title |
A Global Online Handwriting Recognition Approach Based on Frequent Patterns |
title_short |
A Global Online Handwriting Recognition Approach Based on Frequent Patterns |
title_full |
A Global Online Handwriting Recognition Approach Based on Frequent Patterns |
title_fullStr |
A Global Online Handwriting Recognition Approach Based on Frequent Patterns |
title_full_unstemmed |
A Global Online Handwriting Recognition Approach Based on Frequent Patterns |
title_sort |
global online handwriting recognition approach based on frequent patterns |
publisher |
D. G. Pylarinos |
series |
Engineering, Technology & Applied Science Research |
issn |
2241-4487 1792-8036 |
publishDate |
2018-06-01 |
description |
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.
|
topic |
frequent features mining frequent patterns spatio-temporal relations minimum threshold online handwriting recognition |
url |
http://etasr.com/index.php/ETASR/article/view/1784 |
work_keys_str_mv |
AT cgmati aglobalonlinehandwritingrecognitionapproachbasedonfrequentpatterns AT hamiri aglobalonlinehandwritingrecognitionapproachbasedonfrequentpatterns AT cgmati globalonlinehandwritingrecognitionapproachbasedonfrequentpatterns AT hamiri globalonlinehandwritingrecognitionapproachbasedonfrequentpatterns |
_version_ |
1724405083172503552 |