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 MoyoSupervisors: Dr Greg Foster and Professor Shaun Bangay.
Presentation Outline
• Problem Statement
• Objectives
• Approach
• Research Done
• Conclusion
Problem Statement
• Hair identification in Zoology and Forensics
• Subjectivity
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.
Approach to the Study:
• Lack of literature focused on hair recognition• Multi-disciplinary nature• New process designed
Approach to the Study:Process Stages
SensorFeature
Generation
Feature
Selection
Classifier
Design
System
Evaluation
Figure Adapted from Theodoris et al (2003:6)
Image Capture
• Each stage detailed next
Research Done:
• How can hair pattern images be captured?
– Based in Zoology Department
– 2 approaches considered
Image Capture
SEMLight Microscope
Research Done:Image Capture
SEMLight Microscope
Scale Patterns
Cross Section Patterns
• Scale Patterns– Use SEM– Better representation of texture in image
Research Done:Image Capture
SEMLight Microscope
• Cross section patterns– Use Light microscope– 2D shape preferred to a 3D shape
Research Done:Image Capture
SEMLight Microscope
• Decisions affecting design– Scale patterns texture based
– Cross section patterns shape based
– 2 separate sub-processes
– Decision not to combine their results
Research Done:Image Capture
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
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
Research Done:Sensor Stage
Original Thresholding
Edge Detection Grab Cut + Thresholding
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
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
Research Done:Feature Extraction
How can features be extracted?
• Cross Section Processing
– Hu’s 7 moments
– RST invariant shape descriptors
– Calculated from central moments
– Require black and white image
Research Done:Feature Selection
What selection of features is necessary
• Scale Pattern Processing
– Image tessellation
– Use of variance or average absolute deviation
Research Done:Feature Selection
What selection of features is necessary?
• Cross section processing
– None required for Hu’s moments
– Would affect scalability of the process
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
Research Done: Results
• From implementation using:– ImageJ plugins written in Java 1.4– 25 scale patterns processed– 50 cross section patterns processed
Research Done: Results
Scale pattern results (Variance)
0%
10%
20%
30%
40%
50%
60%
4 Filters 8 Filters 16 Filters
Number of Filters
% C
orr
ect
Cla
ssif
icati
on
s
Best
Worst
Changes
Research Done: Results
Scale pattern results (AAD)
0%
10%
20%
30%
40%
50%
60%
70%
80%
4 Filters 8 Filters 16 Filters
Number of Filters
% C
orr
ect
Cla
ssif
icati
on
s
Best Case
Worst Case
Changes
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
Research Done: Results
Cross section pattern results
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
BlueWildebeest
Impala Jackal Springbok Zebra
Species
% C
orr
ect
Cla
ssif
icati
on
s
Euclidean
Hamming
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
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.
Questions
• Manual Preparation Work
• Sensor
• Feature extraction
• Feature Selection
• Classifier Design
• Results