Other Free Encyclopedias » Online Encyclopedia » Encyclopedia - Featured Articles » Contributed Topics from F-J

Face Recognition, 3D

techniques images based facial

Definition: Three-dimensional (3D) face recognition techniques exploit information about the 3D shape of the human face.

The majority of existing face recognition algorithms use 2D intensity images of the face. Although such systems have advanced to be fairly accurate under controlled conditions, extrinsic imaging parameters such as pose and illumination are still responsible for serious deterioration of their performance. To improve performance under these conditions, three-dimensional (3D) face recognition techniques have been proposed, that exploit information about the 3D shape of the human face. The use of 3D images for personal identification is based on the intuitive notion that the shape of faces can be highly discriminatory and is not affected by changes in lighting or by facial pigment.

The 3D geometry of the human face may be acquired by means of special sensors, including laser scanners, 3D cameras based on structured light or stereo vision techniques (see Figure 1). Although significant advances have been made in 3D sensor technology, there are still several factors that limit their wide application, such as acquisition time, cost, spatial and depth accuracy, depth of field, existence of artifacts and missing points.

The earliest approach adopted towards 3D face recognition is based on the extraction of 3D facial features by means of differential geometry techniques. Commonly, surface properties such as curvature are used to localize facial features invariant to rigid transformations of the face, which are subsequently used to match face images. More sophisticated techniques, such as the Point Signatures, have been proposed for 3D face matching. Point Signatures describe the local structure of face points and are used to find correspondences between 3D faces. Recognition is based on the similarity of signature vectors in respective facial points.

Appearance based methods like PCA simplify 3D data processing by using 2D depth images (see Fig. 1b), where pixel values represent the distance of corresponding points from the camera. The main problem of such techniques is alignment of 3D images and pose variations, but it can be overcome, since 3D data can be exploited for accurate pose estimation and compensation. The combination of 2D and 3D images for multimodal face recognition using PCA has also been proposed, and significant performance improvement has been achieved.

Face Recognition Evaluation and Pilots [next] [back] Face Recognition - Face Detection, Global Approaches for, Feature Based Techniques, Problems and Considerations, Conclusions and Future Developments

User Comments

Your email address will be altered so spam harvesting bots can't read it easily.
Hide my email completely instead?

Cancel or