Abstract:
Deaf people use Sign Language and
Fingerspelling as a fundamental communication
method. Fingerspelling or manual spelling is a
method of spelling words using hand movements, and
most often used to spell out names of people, places,
organizations, books and other words for which no
sign exists. In this experiment, the images for 31 static
fingerspelling characters of Myanmar consonant are
used as the input images. Three feature vectors
extraction methods (SIFT, SURF, and BRIEF) were
done separately on our collected Myanmar Sign
Language (MSL) fingerspelling images. MSL
fingerspelling data are classified with seven different
approaches; Multilayer Perceptron, Gaussian Naïve
Bays, Decision Tree, Logistic Regression, Random
Forest, Support Vector Machine and K-Nearest
Neighbor. In this paper, we provide the performance
results of different features on different classifiers and
the highest classification rate is up to 97% with SURF
feature and Random Forest classifier. Moreover, 10-
fold cross validation was made in our experiment and
we provide the classification results for each
classifier.
Description:
We would like to thank the headmaster,
teachers and students from Mary Chapman School for
the Deaf, Yangon and all participants for their kind
contributions to our research input experiments. We
would like to thank JICA EEHE Project (Project for
Enhancement of Engineering Higher Education in
Myanmar) for their supporting of research fund to our
research.
