Gesture recognition using support Vector machine
The Sign language is very important for people who have hearing and speaking deficiency generally called Deaf
and Mute. It is the only mode of communication for such people to convey their messages and it becomes very important for
people to understand their language. In this paper, we have implemented the algorithm of extracting Histogram of Gradient
Orientation (HOG) features and these features are used to pass in an Support Vector Machine (SVM) to construct a training
model which will further classify the test images given by the user depending on the respective feature vector. We have
developed a system to recognize alphabets characters using two feature vectors namely HOG and Scale Invariant Feature
Transform (SIFT) features and tested both of them such that it will give the optimal result . The real time images will be
captured first by means of webcam and then stored in directory and on recently captured image, feature extraction will take
place to identify which sign has been articulated by the user through algorithm in MATLAB. After the comparison, the result
will be produced in accordance with the input image to the image stored for a specific letter already in the database.
Keywords- HOG, libSVM, SIFT, SVM, Vision based hand Gesture.