4. Facial recognition systems are built on computer programs
that analyze images of human faces for the purpose of
Identifying them.
The programs take a facial image, measure characteristics such
as the distance between the eyes, the length of the nose, and
the angle of the jaw, and create a unique file called a
"template."
7. Perhaps the most famous early example of a face recognition
system is due to Kohonen , who demonstrated that a simple
neural net could perform face recognition for aligned and
normalized face images.
Kirby and Sirovich (1989) later introduced an algebraic
manipulation which made it easy to directly calculate the
eigenfaces, and showed that fewer than 100 were required
to accurately code carefully aligned and normalized face
images.
Face Recognition using Elastic Graph Matching
8.
9. Laplacianfaces refer to
an appearance-based
approach to human face
representation and
recognition. The approach
uses
Locality Preserving Projection
(LPP) to learn a locality
preserving subspace which
seeks to capture the
intrinsic geometry of the
data and the local
structure.
When the projection is obtained, each face image
in the image space is mapped to the low-
dimensional face subspace, which is characterized
by a set of feature images, they are
called Laplacianfaces.
10. Principle Component Analysis(PCA) is
an eigenvector method designed to
model linear variation in high-
dimensional data.
Locality Preserving Projections (LPP),
the face images are mapped into a
face subspace for analysis.
and Linear Discriminant Analysis
(LDA) which effectively see only the
Euclidean structure of face space,
Two-dimensional linear embedding of face images by Laplacianfaces. As can be
seen, the face images are divided into two parts, the faces with open mouth and
the faces with closed mouth. Moreover, it can be clearly seen that the pose and
expression of human faces change continuously and smoothly,
from top to bottom, from left to right. The bottom images correspond to points
along the right path (linked by solid line illustrating one particular mode of
variability in pose.
14. 2. Image Based Projection Techniques
Laplacian is based upon the processing
of images.
Input Image
Matched Image
Processing
15. KDT Algorithm
The utilization of the KDT algorithm is quite effective in
speeding up the kNN query process.
By adopting the KDT method, the
2D Laplacianfaces is improved to
be not only more efficient for
training, but also as competitively
fast as other methods for query
and classification.
3D Tree
16. Face hallucination
Face hallucination is super-resolution of face images, or
clarifying the details of a face from a low-resolution image. The
technique of sparse coding can be used. Because of the
importance of face images in facial recognition systems and
other applications, face hallucination has become an area of
research.
17. Camera Technology
Cameras can be used to detect the Faces and recognize a
particular person
"Camera technology designed to
spot potential terrorists by their
facial characteristics at airports
failed its first major test at
Boston's Logan Airport"
To Search Someone
18. LIMITATIONS
The human face has 80 nodal points, of which facial
recognition software utilizes 14 to 22.
Less accurate
Only pgm file is used
Does not deal with manifold structure
It doest not deal with biometric characteristics
19. FUTURE SCOPES• A new dimension to facial recognition-3d
• Unobtrusive audio-and-video based person identification systems.
• Neven Vision, www.nevenvision.com a Santa Monica, Calif.-based
developer of mobile machine vision technology.
Neven Vision
3D Face
Expression
Unobtrusive
20. REFERENCES[1] A. U. Batur and M. H. Hayes, “Linear Subspace for Illumination
Robust Face Recognition”, IEEE
Int. Conf. on Computer Vision and Pattern Recognition, Hawaii, Dec. 11-
13, 2001.
[2] P. N. Belhumeur, J. P. Hespanha and D. J. Kriegman, “Eigenfaces vs.
Fisherfaces: Recognition Using Class Specific Linear Projection”, IEEE
Trans. Pattern Analysis and Machine Intelligence, vol.
19, No. 7, 1997, pp. 711-720.
[3] M. Belkin and P. Niyogi, “Laplacian Eigenmaps and Spectral
Techniques for Embedding and Clustering”, Advances in Neural
Information Processing System 15, Vancouver, British Columbia, Canada,
2001.
[4] M. Belkin and P. Niyogi, “Using Manifold Structure for Partially
Labeled Classification”, Advances
in Neural Information Processing System 15, Vancouver, British
Columbia, Canada, 2002.
[ ]
21. Now We Know
What is Face Recognition?
Its History
What Technology is used?
What are its Features?
Its limitations and Future?