Extraction of regions of interest from face images using cellular analysis

ABSTRACT

A novel algorithm for extracting the regions of interest (ROI) from face images is presented in this paper. The novelty of the algorithm comes from its multi-resolution cellular analysis coupled with an adaptive thresholding technique incorporating a unique idea of exponential averaging. The complexity of the cellular ROIs reported by the algorithm from the frontal face view as input, is further controllable by the chosen cell size, which is its added advantage. Apart from the actual ROIs representing the eye pair, nostrils, and the mouth area, some regions of non-interest may also creep in while extracting the set of cellular regions from the face image, which are discarded by a simple geometric analysis using a containment tree. The containment tree, which is newly introduced in this paper, captures the underlying relationship of the cellular regions, which, when analyzed, returns the face ROIs in an elegant representation. Since the entire algorithm works purely in the integer domain with primitive operations (comparison, right shift, and addition) only, it runs very fast for both gray-scale and color images. Some experimental results on different facial images demonstrate its speed, robustness, and efficiency.

REFERENCES

• 1: R. Brunelli , T. Poggio, Face Recognition: Features Versus Templates, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.15 n.10, p.1042-1052, October 1993 [doi>10.1109/34.254061]
• 2: K. I. Chang, K. W. Bowyer, and P. J. Flynn, Multiple Nose Region Matching for 3D Face Recognition under Varying Facial Expression, Proc. First Intl. Workshop Automatic Face and Gesture Recognition, vol. 28, no. 10, pp. 1695--1700, 2006.
• 3: R. Chellappa, C. L. Wilson, and S. Sirohey, Human and Machine Recognition of Faces: A Survey, Proc. IEEE, vol. 83, no. 5, pp. 705--740, 1995.
• 4: C. W. Chen, J. Luo, and K. J. Parker, Image Segmentation via Adaptive K-mean Clustering and Knowledge-based Morphological Operations with Biomedical Applications. IEEE Trans. Image Processing, vol. 7, no. 12, pp. 1673--1683, 1998.
• 5: Ian Craw , David Tock , Alan Bennett, Finding Face Features, Proceedings of the Second European Conference on Computer Vision, p.92-96, May 19-22, 1992
• 6: http://www.cl.cam.ac.uk/Research/DTG/attarchive:pub/data/-attfaces.tar.Z. AT&T\The Database of Faces" (formerly\The ORL Database of Faces"). AT&T Laboratories, Cambridge.
• 7: http://cbcl.mit.edu/software-datasets/heisele/facerecognition-Database.html. MIT-CBCL Face Recognition Database.
• 8: B. Duc, S. Fisher, and N. J. Bigäun, Face authentication with Gabor information on deformable graphs, IEEE Trans. Image Proc., vol. 8, no. 4, pp. 504--516, 1999.
• 9: S. Eickler, S. Mäuller, and G. Rigoll and A. Jacquin, Recognition of JPEG compressed face images based on statistical methods, Image Vis. Comput., vol. 18, no. 4, pp. 279--287, 2000.
• 10: A. Eleftheriadis and A. Jacquin, Automatic face location, detection and tracking for model-assisted coding of video teleconferencing sequences at low-bit rates, Signal Processing: Image Communication, vol. 7, no. 3, pp. 23--248, 1995.
• 11: H. P. Graf, T. Chen, E. Petajan, and E. Cosatto, Locating Faces and Facial Parts, Proc. First Int. S1 Workshop Automatic Face and Gesture Recognition, pp. 41--46, 1995.
• 12: M. Hamouz , J. Kittler , J. -K. Kamarainen , P. Paalanen , H. Kalviainen , J. Matas, Feature-Based Affine-Invariant Localization of Faces, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.27 n.9, p.1490-1495, September 2005 [doi>10.1109/TPAMI.2005.179]
• 13: Yea-Shuan Huang , Hao-ying Cheng , Po-Feng Cheng , Cheng-Yuan Tang, Face Detection with High Precision Based on Radial-Symmetry Transform and Eye-Pair Checking, Proceedings of the IEEE International Conference on Video and Signal Based Surveillance, p.62, November 22-24, 2006 [doi>10.1109/AVSS.2006.49]
• 14: Constantine Kotropoulos , Ioannis Pitas , Stefan Fischer , Benoît Duc, Face Authentication Using Morphological Dynamic Link Architecture, Proceedings of the First International Conference on Audio- and Video-Based Biometric Person Authentication, p.169-176, March 12-14, 1997
• 15: K. Lam and H. Yan, Fast Algorithm for Locating Head Boundaries, Electronic Imaging, vol. 3, no. 4, pp. 351--359, 1994.
• 16: Baback Moghaddam , Alex Pentland, Probabilistic Visual Learning for Object Representation, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.19 n.7, p.696-710, July 1997 [doi>10.1109/34.598227]
• 17: Ashok Samal , Prasana A. Iyengar, Automatic recognition and analysis of human faces and facial expressions: a survey, Pattern Recognition, v.25 n.1, p.65-77, Jan. 1992 [doi>10.1016/0031-3203(92)90007-6]
• 18: P. Sankaran , S. Gundimada , R. C. Tompkins , V. K. Asari, Pose Angle Determination by Face, Eyes and Nose Localization, Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops, p.161, June 20-26, 2005 [doi>10.1109/CVPR.2005.582]
• 19: K. Sobottka, and I. Pitas, A novel method for automatic face segmentation, facial feature extraction and tracking, Signal Processing: Image Communication, vol. 12, no. 3, pp. 263--281.
• 20: Matthew Turk , Alex Pentland, Eigenfaces for recognition, Journal of Cognitive Neuroscience, v.3 n.1, p.71-86, Winter 1991 [doi>10.1162/jocn.1991.3.1.71]
• 21: Ming-Hsuan Yang , David J. Kriegman , Narendra Ahuja, Detecting Faces in Images: A Survey, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.24 n.1, p.34-58, January 2002 [doi>10.1109/34.982883]
• 22: W. Zhao , R. Chellappa , P. J. Phillips , A. Rosenfeld, Face recognition: A literature survey, ACM Computing Surveys (CSUR), v.35 n.4, p.399-458, December 2003 [doi>10.1145/954339.954342]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.6 Segmentation

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
        I.4.10 Image Representation
      I.4.7 Feature Measurement

Keywords:
adaptive thresholding, biometrics, containment tree, face segmentation, region of interest