1. Eigenedginess vs. Eigenhill, Eigenface and Eigenedge by
S. Ramesh, S. Palanivel, Sukhendu Das and B. Yegnanarayana
Department of Computer Science and Engineering
IIT Madras, Chennai, INDIA
Artificial Neural Networks Lab IIT Madras

2. Different Representations of face
Grey level image
Suffers illumination problem
Edge map
Locality problem
Spread edge profile (called hills)
Carries artificial edginess of the face
Edginess image
Carries natural variations present in the face image
Artificial Neural Networks Lab IIT Madras

3. 1-D Processing of images for edge/edginess extraction
Smoothing filter: 1-D Gaussian function
where 1 is the spatial spread of the Gaussian
Differential Operator: First derivative of
Gaussian function
where 2 is the spatial spread of the Gaussian
Artificial Neural Networks Lab IIT Madras

4. 1-D Processing of images for edge/edginess extraction (contd.)
Method of 1-D processing
Smoothing filter is applied along the horizontal scan lines of the image
For the Smoothing filter output, the differential operator is applied along the vertical direction to extract the horizontal components of the edginess (strength of an edge)
The process is repeated similarly in the orthogonal direction
Finally the horizontal and vertical components of the edginess are combined to obtain the edginess map of the image
Advantages of 1-D processing
Better tolerance to noise than Canny’s operator
Computational time reduced to 10% of 2D processing
Artificial Neural Networks Lab IIT Madras

5. Artificial Neural Networks Lab IIT Madras
Results
Grey level images
Edge images
Edginess images
Artificial Neural Networks Lab IIT Madras

6. Artificial Neural Networks Lab IIT Madras
Eigenedginess
If x1, x2, ….., xP of N dimension are the input patterns, then the transformed lower dimension patterns (of M dimension) y1, y2, ….., yP are given by
yi = WT xi, i = 1,2,....,P
W = [e1 e2 …. eM]N*M, where ei is the eigenvector associated with eigenvalues 1 2 …… M (M < N).
ei and i are eigenvectors and eigenvalues obtained by solving the eigenstructure equation:
C ei = i ei, where C = (xp - ) (xp - )T and  = xp
Eigenvectors of the covariance matrix(C) of the edginess images are referred as eigenedginess
Artificial Neural Networks Lab IIT Madras

7. Comparative illustration of the first three Eigenvectors
Eigenface
Eigenedge
Eigenhill
Eigenedginess
Comparative illustration of the first three Eigenvectors
of faces, using all the four techniques

8. Face Recognition performance
(Out of 80 faces)
Artificial Neural Networks Lab IIT Madras

9. Processing Stages 1-D Processing Input Image Edginess Image
Eigen Analysis
Eigenedginess:
1-D Processing
Input Image
Edginess
Image
Eigen Analysis
Transformation Function
Transformed edginess:
Artificial Neural Networks Lab IIT Madras

10. Artificial Neural Networks Lab IIT Madras
Transformed Edginess
Artificial Neural Networks Lab IIT Madras
Transformation function

11. Results of eigenanalysis with Transformed edginess
Artificial Neural Networks Lab IIT Madras
The transformation function was used with: x1=0 and y3=0

12. Effect of first few eigenvectors
Artificial Neural Networks Lab IIT Madras

13. Recognition performance due to variations in facial expression
Artificial Neural Networks Lab IIT Madras

14. Artificial Neural Networks Lab IIT Madras
Summary
Concept of edginess of an image is introduced for face recognition, which is invariant to illumination and facial expression.
Experimental results show that the performance of Eigenedginess representation is better than eigenhill, eigenface and eigenedge for face recognition.
Performance of face recognition using transformed edginess image and the effect of first few eigenvectors are also discussed.
Artificial Neural Networks Lab IIT Madras

15. Artificial Neural Networks Lab IIT Madras
References
R. Brunelli and T. Poggio, “Face recognition: features versus templates”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.15, no.10, pp , October 1993.
M. Turk and A. Pentland, “Eigenfaces for recognition”, Journal of Cognitive Neuro-Science, vol.3, pp , 1991.
Yilmaz, Alper and M.Gokmen, “Eigenhill vs. eigenface and eigenedge”, Pattern Recognition, vol.34, pp , 2001.
P. Kiran Kumar, Sukhendu Das and B. Yegnanarayana, “One-Dimensional processing of images”,in International Conference on Multimedia Processing and Systems, IIT Chennai, India, pp , August 13-15, 2000.
Artificial Neural Networks Lab IIT Madras

16. Artificial Neural Networks Lab IIT Madras
Thank You
Artificial Neural Networks Lab IIT Madras