Image Pattern Recognition

1
Image Pattern Recognition

• The identification of animal species through the
  classification of hair patterns using image
  pattern recognition A case study of identifying
  cheetah prey.

Principal Investigator Thamsanqa
Moyo Supervisors Dr Greg Foster and Professor
Shaun Bangay.
2
Presentation Outline

• Problem Statement
• Objectives
• Approach
• Research Done
• Conclusion

3
Problem Statement

• Hair identification in Zoology and Forensics
• Subjectivity

4
Problem Statement

• First application of automated image pattern
  recognition techniques to the problem of
  classifying African mammalian species using hair
  patterns.
• based on the numerical and statistical analysis
  of hair patterns.

5
Approach to the Study

• Lack of literature focused on hair recognition
• Multi-disciplinary nature
• New process designed

6
Approach to the StudyProcess Stages
Feature Generation
Feature Selection
Classifier Design
System Evaluation
Image Capture
Sensor

• Each stage detailed next

Figure Adapted from Theodoris et al (20036)
7
Research Done
Image Capture

• How can hair pattern images be captured?
• Based in Zoology Department
• 2 approaches considered

Light Microscope
SEM
8
Research Done
Image Capture
SEM
Light Microscope

Scale Patterns
Cross Section Patterns
9
Research Done
Image Capture

• Scale Patterns
• Use SEM
• Better representation of texture in image

Light Microscope
SEM
10
Research Done
Image Capture

• Cross section patterns
• Use Light microscope
• 2D shape preferred to a 3D shape

Light Microscope
SEM
11
Research Done
Image Capture

• Decisions affecting design
• Scale patterns texture based
• Cross section patterns shape based
• 2 separate sub-processes
• Decision not to combine their results

12
Research Done Sensor

• What image manipulation techniques are applied in
  a hair pattern recognition process?
• Scale Pattern Processing
• User defined ROI
• Handle RST variations
• No need to cater for reflection variations
• Convert to greyscale

13
Research Done Sensor Stage

• What image manipulation techniques are applied in
  a hair pattern recognition process?
• Cross section pattern processing
• User defined ROI
• Image segmentation and thresholding
• Challenges

14
Research Done Sensor Stage
Original
Thresholding
Edge Detection
Grab Cut Thresholding
15
Research Done
Sensor Stage

• Findings
• Most sensitive stage of the process
• Cross section patterns best extracted with Grab
  Cut
• Contributions
• First test of Grab Cut technique in a real world
  problem

16
Research Done Feature Extraction

• How can features be extracted?
• Scale Pattern Processing
• Gabor filters
• Capture pattern orientation and frequency
  information
• Produces n number of filtered images where n is
  the size of the Gabor filter-bank

17
Research Done Feature Extraction
Filtered Images from a Gabor Filter of size 4.
Images filtered at initial orientation of 0
degrees
Images filtered at initial orientation of 180
degrees
18
Research Done Feature Extraction

• How can features be extracted?
• Cross Section Processing
• Hus 7 moments
• RST invariant shape descriptors
• Calculated from central moments
• Require black and white image

19
Research Done Feature Selection

• What selection of features is necessary
• Scale Pattern Processing
• Image tessellation
• Use of variance or average absolute deviation

20
Research Done Feature Selection

• What selection of features is necessary?
• Cross section processing
• None required for Hus moments
• Would affect scalability of the process

21
Research Done Classifier Design

• What mechanisms can be used to classify features?
• Scale Pattern Processing
• Euclidean distance measure
• 3 Scale patterns used to train
• Cross Section Processing
• Euclidean distance measure or Hamming distance
  measure
• 10 cross section patterns used to train

22
Research Done Results

• From implementation using
• ImageJ plugins written in Java 1.4
• 25 scale patterns processed
• 50 cross section patterns processed

23
Research Done Results
Scale pattern results (Variance)
24
Research Done Results
Scale pattern results (AAD)
25
Research Done Results

• Summary of scale pattern results
• AAD is a better feature selection method
• Results most stable with 8 filters using AAD as
  feature selector
• Explanation of this result

26
Research Done Results
Cross section pattern results
27
Research Done Results

• Summary of cross section pattern results
• Euclidean distance overall classification rate
  26
• Hamming distance overall classification rate 40
• Explanation of this result

28
Conclusion

• Findings and Contributions
• Gabor filters and moments shown to provide hair
  pattern classification information
• AAD performs better feature selection than
  variance
• Hamming distance more suitable classifier of
  moments than Euclidean distance
• First application of hair pattern recognition on
  African mammalian species hair.

29
Questions

• Manual Preparation Work
• Sensor
• Feature extraction
• Feature Selection
• Classifier Design
• Results