登入選單
返回Google圖書搜尋
3D Face Recognition in a Ambient Intelligence Environment Scenario
註釋We presented a 3D face recognition method applied to an Ambient Intelligence Environment. The proposed approach to acquisition and recognition proved to be suited to the applicative context thanks to high accuracy and recognition speed, effectively exploiting the advantages of face over other biometrics. As the acquisition system requires the user to look at a specific target to allow a valid face capture, we are working on a multi-angle stereoscopic camera arrangement, to make this critical task less annoying and more robust to a wide posing range. This 3D face recognition method based on 3D geometry and color texture is aimed to improve robustness to presence/absence of beard and to expressive variations. It proved to be simple and fast and experiments conducted showed high average recognition rate and a measurable effectiveness of both flesh mask and expression weighting mask. Ongoing research will implement a true multi-modal version of the basic algorithm with a second recognition engine dedicated to the color info (texture) which could further enhance the discriminating power.