Open Access Open Access  Restricted Access Subscription Access

Partial Face Recognition using Phase Only Correlation (POC)


Affiliations
1 Department of Information Technology, RCC Institute of Information Technology, Kolkata - 700015, West Bengal, India
2 Department of Information Technology, RCC Institute of Information Technology, Kolkata-700015, India
 

Numerous methods have been developed for holistic face recognition with impressive performance. But Partial faces frequently appear in unconstrained scenarios, with images captured by surveillance cameras or handheld devices (e.g., mobile phones) in particular. In this paper, a method for automatically recognizing partial human face images is presented. The technique uses the Phase-Only Correlation (POC) for image matching. Experiment was conducted on a database of 479 images of 40 different persons. For experimental evaluation, a mask was generated on every query image to identify and separate the non-occluded portions. These separated portions were compared with the gallery images using the POC technique. Results have shown the proposed method is practical and provides preferable performance.

Keywords

Occlusion, Partial Face, Phase Only Correlation.
User
Notifications
Font Size

  • Cootes TF, Taylor CJ, Cooper D, Graham J. Active shape models-their training and application. Computer Vision and Image Understanding. 1995 Jan; 61(1):38–59.
  • Cootes T, Edwards G, Taylor C. Active appearance models. IEEE Trans Pattern Analysis and Machine Intelligence. 2001 Jun; 23(6):681–5.
  • Yang J, Liao S, Li SZ. Automatic partial face alignment in NIR video sequences. Proceedings of IAPR/IEEE 3rd International Conference on Biometrics; 2009.
  • Yi D, Liao S, Lei Z, Sang J, Li S. Partial face matching between near infrared and visual images in MBGC portal challenge. Proceedings of IAPR/ IEEE 3rd International Conference on Biometrics; 2009.
  • Beymer D. Face recognition under varying pose. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition; 1994 Jun. p. 756–61.
  • Pentland A, Moghaddam B, Starner T. View-based and modular Eigenspaces for face recognition. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition; 1994. p. 84–91.
  • Vetter T, Poggio T. Linear objects classes and image synthesis from a single example image. IEEE Trans Pattern Analysis and Machine Intelligence. 1997 Jul; 19(7):733–41.
  • Graham D, Allison N. Face recognition from unfamiliar views: Subspace methods and pose dependency. Proceedings of 3rd International Conference on Automatic Face and Gesture Recognition; 1998. p. 348–53.
  • Wiskott L, Fellous J-M, Kruger N, von der Malsburg C. Face recognition by elastic bunch graph matching. IEEE Trans Pattern Analysis and Machine Intelligence. 1997 Jul; 19(7):775–9.
  • Blanz V, Romdhani S, Vetter T. Face identification across different poses and illumination with a 3D Morphable model. Proceedings of 5th International Conference on Face and Gesture Recognition; 2002. p. 202-7.
  • Gross R, Matthews I, Baker S. Fisher light-fields for face recognition across pose and illumination. Proceedings of German Symposium Pattern Recognition; 2002. p. 481–9.
  • Heisele B, Ho P, Wu J, Poggio T. Face recognition: Component-based versus global approaches. Computer Vision and Image Understanding. 2003; 91(1/2):6–21.
  • Sato K, Shah S, Aggarwal J. Partial face recognition using radial basis function networks. Proceedings of IEEE 3rd International Conference on Automatic Face and Gesture Recognition; 1998. p. 288–93.
  • Gutta S, Philomin V, Trajkovic M. An investigation into the use of partialfaces for face recognition. Proceedings of International Conference on Automatic Face and Gesture Recognition; 2002. p. 33–8.
  • Park U, Ross A, Jain A. Periocular biometrics in the visible spectrum: A feasibility study. Proceedings of IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems; 2009.
  • Martinez A. Recognizing imprecisely localized, partially occluded, and expression variant faces from a single sample per class. IEEE Trans Pattern Analysis and Machine Intelligence. 2002 Jun; 24(6):748–63.
  • Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: Application to face recognition. IEEE Trans Pattern Analysis and Machine Intelligence. 2006 Dec; 28(12):2037–41.
  • Pan K, Liao S, Zhang Z, Li S, Zhang P. Part-based face recognition using near infrared images. Proceedings of IEEE International Workshop Object Tracking and Classification in and Beyond the Visible Spectrum; 2007.
  • Min R, Hadid A, Dugelay J-L. Improving the recognition of faces occluded by facial accessories. Proceedings of IEEE Conference Automatic Face and Gesture Recognition; 2011.
  • Brunelli R, Poggio T. Face recognition: Features versus templates. IEEE Trans Pattern Analysis and Machine Intelligence. 1993 Oct; 15(10):1042–52.
  • Pentland A, Moghaddam B, Starner T. View-based and modular Eigenspaces for face recognition. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition; 1994. p. 84–91.
  • Heisele B, Ho P, Wu J, Poggio T. Face recognition: Component-based versus global approaches. Computer Vision and Image Understanding. 2003; 91(1/2):6–21.
  • Oppenheim AV, Lim JS. The importance of phase in signals. IEEE Proceedings; 1981. p. 529–41.
  • Takita K, Aoki T, Sasaki Y, Higuchi T, Kobayashi K. High-accuracy subpixel image registration based on phase-only correlation. IEICE Trans Fundamentals. 2003 Aug; E86-A(8):1925–34.
  • Gueham M, Bouridane A, Crookes D. Automatic recognition of partial shoeprints based on Phase-Only Correlation. IEEE International Conference on Image Processing; 2007.
  • Liao S, Jain AK, Li SZ. Partial face recognition: Alignment-free approach. IEEE International Joint Conference on Biometrics Compendium (IJCB); 2011.
  • CSU Face Identification Evaluation System. 2012. Available from: http:// www.cs. colostate.edu/evalfacerec/
  • Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: Application to face recognition. IEEE Trans Pattern Analysis and Machine Intelligence. 2006 Dec; 28(12):2037–41.
  • Phillips PJ, Grother P, Micheals R. Evaluation Methods in Face Recognition. Handbook of Face Recognition. 2nd ed. In: Li SZ, Jain AK, editors. 2011 Sept. p. 551–74.

Abstract Views: 497

PDF Views: 148




  • Partial Face Recognition using Phase Only Correlation (POC)

Abstract Views: 497  |  PDF Views: 148

Authors

Sayantika Debnath
Department of Information Technology, RCC Institute of Information Technology, Kolkata - 700015, West Bengal, India
Arpita Pramanik
Department of Information Technology, RCC Institute of Information Technology, Kolkata - 700015, West Bengal, India
Hiranmoy Roy
Department of Information Technology, RCC Institute of Information Technology, Kolkata-700015, India

Abstract


Numerous methods have been developed for holistic face recognition with impressive performance. But Partial faces frequently appear in unconstrained scenarios, with images captured by surveillance cameras or handheld devices (e.g., mobile phones) in particular. In this paper, a method for automatically recognizing partial human face images is presented. The technique uses the Phase-Only Correlation (POC) for image matching. Experiment was conducted on a database of 479 images of 40 different persons. For experimental evaluation, a mask was generated on every query image to identify and separate the non-occluded portions. These separated portions were compared with the gallery images using the POC technique. Results have shown the proposed method is practical and provides preferable performance.

Keywords


Occlusion, Partial Face, Phase Only Correlation.

References