International Congress on Advanced in Phase Measurement Methods in Optics Metrology and Imaging - Locarno May 2010

1. 17 - 21 May 2010 At Monte Verita, Locarno, Switzerland IR Fringe Projection for 3D Face Recognition Giuseppe Schirripa Spagnolo, Lorenzo Cozzella, Carla Simonetti Dipartimento Ingegneria Elettronica, Università di Roma Tre, Italy e-mail: cozzella@ uniroma3.it - schirrip@uniroma3.it

3. SET-UP

4. Phase Unwrapping and inconsistent region

5. 3D dataset allignement

8. Face recognition systems are the least intrusive from a biometric sampling point of view, requiring no contact, nor even the awareness of the subject.

9. The biometric works, or at least works in theory, with legacy photograph data-bases, videotape, or other image sources

10. Face recognition can, at least in theory, be used for screening of unwanted individuals in a crowd, in real time.

12. Face currently is a poor biometric for use in a pure identification protocol

13. An obvious circumvention method is disguise

16. Video sequence

17. Infrared & near infrared(facial thermogram)

19. Facial Detection

20. Facial Recognition

21. Typical Facial Recognition technology automates the recognition of faces using one of two 2 modeling approaches:

22. Face appearance

23. 2D Eigen faces

24. 3D Morphable Model

25. Face geometry

27. 2D images contain limited information

28. 3D Representation of face is less susceptible to isometric deformations (expression changes).

30. The system In this work, the 3D model of the face is achieved by projecting near infrared light modulated by a sinusoidal fringe pattern on the face.

31. ... continue The system In this work, the 3D model of the face is achieved by projecting near infrared light modulated by a sinusoidal fringe pattern on the face.

32. ... continue The system Structured light is obtained by the interference of the two fields diffracted by a saw-tooth phase grating. The fringe patterns, distorted by the surface roughness, are captured by a high-resolution image camera.

33. ... continue The system The fringe patterns, captured by the image camera, are processed with the aid of the Fourier transform analysis and a procedure of unwrapped phase-map able to minimize and to fill holes generate by shadows and facial hair (like beard, mustache).

34. Phase Unwrapping

35. Example of reconstruction Reconstructed surface Original surface Curves extracted

36. ... continue The system The method is experimentally simple, has a low-cost set-up, requires only single image as input, is easy to be integrated in systems of control and access. The system can work in real time (necessity of an only acquisition) and projecting non visible light (no damages to the retina). The system can be easily hidden so that it is difficult to discover.

37. Face Capture System SET-UP Set up details can be found in: G. Schirripa Spagnolo, D. Ambrosini, "Diffractive optical element-based profilometer for surface inspection", Optical Engineering 40, pp. 44-52 (2001)

38. Face Capture System - SET-UP

39. Face Capture System - SET-UP

40. Procedure

41. Phase Unwrapping and inconsistent region The case of an image containing regions without phase information

43. an initial approximate estimation of the phase data in the region (pixels) of inconsistent data is performed by “standard weighted least-squares algorithm”. At the inconsistent zones is assigned zero weight.

45. Rewrapped phase 20 15 Real unwrapped phase 10 Initial wrapped phase 5 0 -5 -10 -15 Esteemed unwrapped phase -20 -25 0 10 20 30 40 50 60 70 80 90 100

46. Inconsistent data Reconstructed region withbinarymask Procedure that allows to reconstruct the congruence

48. a rewrapping procedure (plus congruence procedure) is used to obtain wrapped phase map without initial inconsistencies;

50. Interpolation of phase data in regions of inconsistent To reduce the problem of regions of inconsistence, another approach consists to acquire (at the same time with more cameras) more images and subsequently to performed data fusion to produce a unique detailed 3D model.

51. Interpolation of phase data in regions of inconsistent Align two partially-overlapping meshesgiven initial guessfor relative transform

53. The algorithm is very simple and is commonly used in real‐time. It iteratively estimates the transformation (translation, rotation) between two raw scans.

55. Estimate the parameters using a mean square cost function.

56. Transform the points using the estimated parameters.

59. 36 Extraction of feature points 23 74

61. Therefore, a new phase unwrapping procedure is realized to minimize and to fill holes generate by shadows and facial hair.

62. The device, in the current configuration, is able to scan human faces in a short time and the face control can be make in "invisible" way.