SBIR Phase II: A Face Idenification System Using a Novel 3D Camera

Genex Technologies，Inc.(GTI)的这个SBIR第二阶段项目的主要目标是研究首次使用新型3D摄像机建立具有复杂3D人脸匹配能力的自动3D人脸ID系统的可行性。3D人脸识别系统的关键组成部分包括：(1)能够实时获取2D和3D人脸图像的新型3D摄像机；(2)基于高效3D人脸识别算法的软件；(3)2D和3D人脸图像数据库；以及(4)用户界面。人脸是一个三维(3D)几何对象，每个人脸都有其独特的3D曲面轮廓。在3D表示中，没有两个人脸是完全相同的，因此可以使用人脸上的3D特征和表面轮廓来快速准确地识别人脸(Face-ID)。由于缺乏低成本的3D成像设备和有效的3D人脸ID算法，几乎所有现有的人脸ID系统都只使用2D灰度人脸图像作为输入。2D图像天生就容易受到光照条件和人脸方向变化的影响，因为它们不能保留人脸的3D几何结构。这一基本限制极大地限制了当前人脸识别系统有效执行人脸识别功能的能力。因此，现有的人脸识别系统在实际应用中的匹配率很低(低于90%)。然而，有了3D相机--一种电子3D成像设备--能够在一张快照中产生人脸的数字3D轮廓测量，GTI系统中提供的3D人脸图像可以提供准确的几何信息，从而实现更准确和更高效的人脸识别。这种3D摄像机作为自动人脸识别系统的一个组件以及除此之外的商业市场是相当大的，应用程序也很多，包括在军事和民用领域。安全和ATM机可以使用Face-ID来验证银行卡用户的身份，从而节省了数百万美元的虚假持卡人声明。计算机访问控制可以使用Face-ID系统而不是密码来授予计算机使用权限。执法人员可以使用Face-ID系统根据逃犯的图像预先选择和抓获他们。军方可以使用人脸识别系统来控制进入限制区域的权限。汽车或船只等有价值的财产可以使用3D Face-ID系统来识别其所有者。低成本的3D摄像头还可以用于许多其他应用，如制成品检测、机器人、自动驾驶汽车和虚拟现实。视频会议和交互式电视的快速发展进一步拓宽了3D成像技术的可能应用。

The primary aim of this SBIR Phase II project from Genex Technologies, Inc. (GTI) is the investigation of the feasibility of building, for the first time, an automatic 3D Face ID system with sophisticated 3D face matching capability using a novel 3D camera. The key components of the 3D Face ID system include: (1)A novel 3D camera that is capable of acquiring both 2D and 3D facial images in real-time; (2) Software based on an efficient 3D face identification algorithm; (3) 2D and 3D facial image database; and (4) A user-interface. The human face is a three-dimensional (3D) geometric object, and each face has its unique 3D surface profile. No two faces are exactly the same in 3D representation; therefore 3D features and surface profiles on a human face can be used for rapid and accurate face identification (face-ID). Because of the lack of low-cost 3D imaging devices and effective 3D face-ID algorithms, almost all existing face-ID systems use only 2D gray-scale face images as their input. The 2D images are inherently vulnerable to changes in the light condition and the face orientation, because they cannot preserve the 3D geometric structure of a face. This fundamental restriction greatly limits the capability of current face-ID systems to effectively perform face recognition functions. As a result, the match-rate for existing face-ID systems in real-world applications is very low (below 90%). However, with a 3D camera--an electronic 3D imaging device-- that is able to produce a digital 3D profile measurement of the human face in one snap shot, the 3D facial images that are available in GTI's system provide accurate geometric information enabling much more accurate and efficient face identification. The commercial market for such a 3D camera as a component of, as well as apart from, automatic face identification systems is sizable, and applications are numerous, including in both military and civilian areas. Security and ATM machines can use Face-ID to verify the identity of bankcard user, saving millions of dollars in false claims of cardholdership. Computer access control can use the Face-ID system instead of a password to grant authority for computer usage. Law enforcement agents can use the Face-ID system to preselect and capture fugitives based on their images. Military can use the Face-ID system to control access to restricted areas. Valuable properties such as cars or boats could use the 3D Face-ID system to identify their owners. Low cost 3D cameras can also be used for many other applications, such as manufactured parts inspection, robotics, autonomous vehicles, and virtual reality. The rapid advances in video-conferencing and interactive television further broaden possible applications of 3D imaging technologies.