Vietnamese Sign Language Recognition using Cross Line Descriptors and Invariant Moments
Main Article Content
Abstract
Sign language is the primary language used by the deaf community in order to convey information through gestures instead of words. Many researches about this language have been done, and they play an important role in life. Currently, most of the hard-of-hearings in Vietnam are facing many difficulties in community integration because of their limited ability. So we propose an approach which can recognize Vietnamese sign language, based on digital image processing combined with a machine learning method. After pre-processing, we use a combination of cross lines descriptors and invariant moments to extract the features, and then the gesture is recognized using support vector machines. This is one of the few studies on sign language applied to Vietnamese alphabet (the number of words is higher and more complex than international standards with several accented letters). The proposed approach has been tested with high accuracy and is promising.
Â
Keywords: gesture; sign; skin color; cross line; invariant moment; kernel function; one-against-all; one-against-one.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.