Sign Language Recognition by Finger Vector
International journal of computing, communication and instrumentation engineering · 2016
The sign language is very important and necessary for deaf since the language is the only way to communicate for deaf and normal people who need to send and receive the messages from the deaf-mute.This paper has suggested a concept of the sign language recognition with finger vectors.A hand figure showing the sign language would be downloaded at runtime using Freeman chaincode attaching on the edge of photos.Then the contour line would appear, detected fingertips and furrows between fingers, that would be transformed to be finger vectors.After that, it could be done by coding and saving in the database in order to compare for recognition further.Moreover, the sign language of 45 samples of number 1-9 were tested, and 98% of accuracy was found.However, this concept has the prominent point because scaling, rotating, thinning or Noise filtering do not need to be done; therefore, it can save up a lot of processing time.