Design and implementation of face recognition-aided IPTV adaptive group recommendation system based on NLMS algorithm

The prototype of multi-facial recognition technique-aided internet protocol television (IPTV) system named “EyeTV” is introduced in this study. EyeTV applies Xbox´s IP camera - KINECT to be the eye of TV for capturing facial features of users, and the multi-facial recognition technique is employed to recognize the user´s identity. The users who watch the videos together are taken as a group, and then the system would automatically memorize the watching history for that group. Besides, the proposed normalized least mean square (NLMS)-based group recommendation technique is embedded in EyeTV for making video recommendation to the memorized groups via their watching history. Group recommendation technique helps group members to make decision quickly without too much time in discussion or debate of video selection. The proposed NLMS-based group recommendation method takes the interactions among the group members for providing more reasonable recommended results.