Object%20Recognition%20in%20the%20Dynamic%20Link%20Architecture

1
Object Recognition in the Dynamic Link
Architecture

• Yang Ran
• CMPS 828J

2
Outline

• Background and Introduction
• System Overview
• General algorithm in details
• Implementations of the algorithm
• Experiment results
• Further readings and conclusion

3
Background

• Problem To recognize human faces from single
  images our of a large gallery.
• Challenges Distortions in terms of position,
  size , expression, and pose
• Existed methods
• Appearance Based v.s. Shape based
• 2D vs. 3D

4
Background Notations

1. Image face image
2. Model face gallery
3. Graph a concise face description
4. Jet A local description of the distribution
   based on the Gabor transform

5
System Overview

1. Faces are represented as rectangular graphs by
   layers of neurons
2. Each neuron represents a node and has a jet
   attached

6
Assumptions

• The image domain and the model domain are
  bi-directionally connected by dynamic links.
• These connections are plastic on a fast time
  scale, changing radically during a single
  recognition event
• The strength of a connection between any two
  nodes in the image and a model is controlled by
  the jet similarity between them, which roughly
  corresponds to the number of features that are
  common to the two nodes

7
Key Factors

• Basic representation is the labeled graph formed
  by edges and vertices bundled in jets
• Edge Labels distance information
• Vertex/Node Labels wavelet responses
• Graph should be able to deform to adapt to the
  variations of human faces

8
Preprocessing by Gabor Wavelets

• Gabor Wavelets are biological motivated
  convolution kernels in the shape of plane waves
  restricted by Gaussian envelope function

9
More for Gabor

• Why use it?
• A good approximation to the sensitivity profiles
  of neurons found in visual cortex of higher
  vertebrates
• Cells come in pair with even and odd symmetry
  like the real and imagery part of Gabor Filter

10
Jets Generation

1. The set of convolution coefficients for kernels
   and frequencies at one image pixel is called a
   jet
2. Describes a small patch of gray values around a
   given pixel
3. Sample W at five logarithmically spaced f levels
   and eight directions by u, v

11
Jets Generation-cntl

• The magnitude of (WI) (kuv, x) form a feature
  vector located at x, which will be referred to as
  a jet
• Evaluate the similarity by Elastic Graph Matching

12
Edge Labels

• Derived from neuron version, edges encodes
  neighborhood relationships
• Presents the topology of the vertices
• Define
• Quadratic comparison function

13
Example

• Graph representation of a face

14
Elastic Graph Matching
Elastic matching of a model graph M to a target
graph I amounts to a search for a set of vertex
positions which simultaneously optimizes the
matching of vertex labels and edge labels
according to
15
Elastic Graph Matching-cntl

• A heuristic algorism is seek to close the optimum
  within a reasonable time
• Step 1 find approximate face position so that
  the image can be scaled and cut to standard size
• Step 2 Extract graph from target face image
• Step 3 Match with cost function
• Refine position and size with ? infinity
• Local distortion

16
Experiments

• Data Base
• Technical Aspects
• Results
• Conclusions

17
Data Base

• As a face data base we used galleries of 111
  different persons. Of most persons there is one
  neutral frontal view, one frontal view of
  different facial expression, and two views
  rotated in depth by 15 and 30 degrees
  respectively.

18
Technical Aspects

• The CPU time needed for the recognition of one
  face against a gallery of 111 models is
  approximately 10--15 minutes on a Sun
  SPARCstation 10-512 with a 50 MHz processor.

19
Results-Office Items
20
Comparison of Two Galleries
21
More Results
22
More Results-cntl
23
Recognition Results Against Galleries
Recognition results against a gallery of 20, 50,
and 111 neutral frontal views
24
Conclusion

• Close to natural model a small number of
  examples is needed for face recognition
• Gabor Wavelets representation are robust to
  moderate lighting changes, shifts and
  deformations
• Elastic Graph Matching in Dynamic Link
  Architecture is robust in face recognition

25
Conclusion

1. Having only several images per person in gallery
   does not provide sufficient information to handle
   3D rotation
2. Rectangle grid v.s. Feature points

26
References

1. M. Lades, J.C. Vorbruggen, J. Buhmann, J. Lange,
   C. von der Malsburg, R.P. Wurtz, W. Konen.
   Distortion Invariant Object Recognition in the
   Dynamik Link Architecture. IEEE Transactions on
   Computers 1992, 42(3)300-311.
2. Laurenz Wiskott, Jean-Marc Fellous, Norbert
   Krüger, et al. Face Recognition by Elastic Bunch
   Graph Matching, Proc. 7th Intern. Conf. on
   Computer Analysis of Images and Patterns,
   CAIP'97, Kiel