Helene Brashear
Valerie Henderson
Kwang-Hyun Park
Harley Hamilton
Seungyon Lee
Thad Starner
Summary:
Goal: Design a ASL gesture recognition system.
A wizard of oz user study was conducted with 5 children to collect gesture data. 541 phrase samples and 1959 sign samples were collected (22 word vocabulary). The system uses a camera and wrist mounted accelerometer to capture motion of the hand. HMM is used to train on the gestures and recognize gestures. Feature vector is combination of the vision data and the accelerometer data. x,y,z of accelerometer data for both hands, x,y change in center position of hand in frames, mass, eccentricity, length of major and minor axis, angle of major axis and direction of major axis in x,y offset. User dependent model of classifier produced 93.39% accuracy and user independent model produced 86.28% accuracy in recognizing gestures.
Discussion:
The data has pruned and the gestures which were seemed to correct were selected for testing. I donot think it is a correct practise to test a recognizer. Also, vocabulary of words used for testing was small.
Comment:
I agree, after all the preparation one would have thought a much larger set of training and testing examples could have been used. At least I got the impression that there were more than five children at the school.
ReplyDeleteI think their approach was really good. However, I think using a data glove, like the one we have in lab, would have made things easier for them.
ReplyDelete