STUDY OF COMPARATION BETWEEN K-MEANS AND SUPPORT VECTOR MACHINE (SVM) ALGORITHM FOR HAND GESTURE RECOGNITION (CASE STUDY: COMMAND FOR BIOLOID ROBOT)
<br /> <br /> Human Robot Interaction (HRI) is useful to assist human to give command to robot. HRI requires media for communication which can be both understood by robot and easily done by human. Usually human using oral language to communicate but there are some situations that requir...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/26539 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | <br />
<br />
Human Robot Interaction (HRI) is useful to assist human to give command to robot. HRI requires media for communication which can be both understood by robot and easily done by human. Usually human using oral language to communicate but there are some situations that require to perform non-verbal activities such as deaf people, patient, and old people, therefore gesture recognition as communication media is needed to give order to Bioloid Robot. SVM and K-Means are algorithm which has high accuracy in several recognition system. This research presents implementation of hand gesture recognition as input command for Bioloid Premium Robot using two methods, K-Means clustering and Support Vector Machine (SVM). Four gestures (forward, right, left and stop) were recognized using Kinect 2.0. The testing was done 1080 times for three distances (2m, 3m, and 4m) and three angle positions (450, 00, dan -450). The SVM required 10ms recognition time with accuracy reaching 95.15%, while K-Means needed 4.45ms recognition time with 77.42% accuracy. This study resulted in Multiclass SVM with DAG decision performs better than K-Means clustering method. <br />
|
|---|