© The Institution of Engineering and Technology
A practical identification system based on 3D face scanning is presented. The speed of comparing a probe scan to the gallery is enabled by scan normalisation followed by extraction of higher level features. Our Canonical Face Depth Map (CFDM) is a standardised representation for three-dimensional (3D) face data in a face-based coordinate system. Our experiments demonstrate that the CFDM normalisation algorithm is (a) robust to noise and occlusion, (b) significantly reduces storage requirements and thus I/O time, and (c) improves the efficiency of face recognition algorithms. Producing the CFDM takes less than a second on a desktop for 320×240 rangel scans. Current 3D scanning and matching methods are too slow for person identification, even for a watch list of only a few hundred face models. Transforming scanned 3D faces into CFDM format enables a probe scan to be matched to hundreds or thousands of gallery scans in a few seconds on a commodity computer. The best results achieved so far are a rank-1 recognition rate of 98.2% and a speed of 1900 face matches per second. Extrapolating these results suggests that multistage systems could achieve even better performance on even larger galleries.
References
-
-
1)
-
Phillips, P.J., Flynn, P.J., Scruggs, T., Bowyer, K.W., Chang, J., Hoffman, K., Marques, J., Min, J., Worek, W.: `Overview of the face recognition grand challenge', Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005.
-
2)
-
P.J. Besl ,
N.D. McKay
.
A method for registration of 3-d shapes.
IEEE Trans. Pattern Anal. Mach. Intelli
,
2 ,
239 -
256
-
3)
-
Conde, C., Serrano, A.: `3D facial normalisation with spin images and influence of range', Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005, p. 115.
-
4)
-
J. Daugman
.
(1998)
Recognizing persons by their iris patterns, personal identification in networked society section 5.
-
5)
-
Colbry, D.: `Human face verification by robust 3d surface alignment', 2006, PhD, Michigan State Unviersity.
-
6)
-
Minolta, Vivid 910 non-contact 3D laser scanner. http://www.konicaminolta.com/sensingusa/products/3d/noncontact/vivid910/index.html, 2008.
-
7)
-
A.K. Jain ,
S.Z. Li
.
(2011)
Handbook of face recognition.
-
8)
-
Boehnen, C., Russ, T.: `A fast multi-modal approach to facial feature detection', Proc. Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION '05), 2004, Breckenridge, Colorado, 01, p. 135–142.
-
9)
-
Chetverikov, D., Svirko, D., Stepanov, D., Kresek, P.: `The trimmed iterative closest point algorithm', Proc. 16th Int. Conf. Pattern Recognition, 2002, Qúebec City, Canada, 3, p. 545–548.
-
10)
-
Boehnen, C., Flynn, P.: `Accuracy of 3D scanning technologies in a face scanning scenario, 3DIM '05', Proc. Fifth Int. Conf. 3-D Digital Imaging and Modeling, 2005, Ottawa, Ontario, Canada, p. 310–317.
-
11)
-
S. Malassiotis ,
M.G. Strintzis
.
Robust face recognition using 2D and 3D data: pose and illumination compensation.
Pattern Recog.
,
2537 -
2548
-
12)
-
G. Stockman ,
J. Payne ,
J. Sadler ,
D. Colbry
.
Error analysis of sensor input variations in a 3D face surface matching system.
Sensor Rev. J
,
2 ,
116 -
121
-
13)
-
Xu, C., Wang, Y., Tan, T., Quan, L.: `Face recognition based on 3D mesh models', Proc. SPIE – The International Society for Optical Engineering, 2004, Denver, CO.
-
14)
-
M. Benz ,
X. Laboureux ,
T. Maier ,
E. Nkenke ,
S. Seeger ,
F.W. Neukam ,
G. Husler
.
The symmetry of faces.
Vision, Modeling, and Visualization
-
15)
-
Y. Wang ,
C. Chua ,
Y. Ho
.
Facial feature detection and face recognition from 2D and 3D.
Pattern Recog. Lett.
,
1191 -
1202
-
16)
-
Colbry, D., Stockman, G., Jain, A.K.: `Detection of anchor points for 3D face verification', Proc. of Workshop Advanced 3D Imaging for Safety and Security, 2005, San Diego, CA.
-
17)
-
Colbry, D., Stockman, G.: `Identity verification via the 3DID face alignment system', Proc. IEEE Workshop on Applications of Computer Vision (WACV), 2007, Austin, TX.
-
18)
-
C. BenAbdelkader ,
P.A. Griffin
.
Comparing and combining depth and texture cues for face recognition.
Image Vis. Comput.
,
339 -
352
-
19)
-
P.J. Phillips ,
P. Grother ,
R.J. Michaels ,
D.M. Blackburn ,
E. Tabassi ,
M. Bone
.
(2003)
Face recognition vendor test (FRVT), overview and summary.
-
20)
-
Savvides, M., Kumar, B.V.K.V., Khosla, P.K.: `Eigenphases vs. eigenfaces', Proc. Int. Conf. Pattern Recognition, 2004, Los Alamitos, CA, USA, 03, p. 810–813.
-
21)
-
B. Manjunath ,
W. Ma
.
Texture features for browsing and retrieval of image data.
Pattern Anal. Mach. Intelli., IEEE Trans.
,
837 -
842
-
22)
-
Dorai, C.: `Cosmos: a framework for representation and recognition of 3D free-form objects', 1996, PhD, Michigan State University.
-
23)
-
3dMD, http://www.3dmd.com/.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2008.0055
Related content
content/journals/10.1049/iet-cvi.2008.0055
pub_keyword,iet_inspecKeyword,pub_concept
6
6