Paper
13 October 2008 3D face database for human pattern recognition
LiMei Song, Lu Lu
Author Affiliations +
Abstract
Face recognition is an essential work to ensure human safety. It is also an important task in biomedical engineering. 2D image is not enough for precision face recognition. 3D face data includes more exact information, such as the precision size of eyes, mouth, etc. 3D face database is an important part in human pattern recognition. There is a lot of method to get 3D data, such as 3D laser scan system, 3D phase measurement, shape from shading, shape from motion, etc. This paper will introduce a non-orbit, non-contact, non-laser 3D measurement system. The main idea is from shape from stereo technique. Two cameras are used in different angle. A sequence of light will project on the face. Human face, human head, human tooth, human body can all be measured by the system. The visualization data of each person can form to a large 3D face database, which can be used in human recognition. The 3D data can provide a vivid copy of a face, so the recognition exactness can be reached to 100%. Although the 3D data is larger than 2D image, it can be used in the occasion where only few people include, such as the recognition of a family, a small company, etc.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
LiMei Song and Lu Lu "3D face database for human pattern recognition", Proc. SPIE 7127, Seventh International Symposium on Instrumentation and Control Technology: Sensors and Instruments, Computer Simulation, and Artificial Intelligence, 71271U (13 October 2008); https://doi.org/10.1117/12.806452
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
3D metrology

3D image processing

Facial recognition systems

Databases

Cameras

Image processing

Pattern recognition

Back to Top