mage classification is a supervised learning problem: define a set of target classes (objects to identify in images), and train a model to recognize them using labeled example photos. Early computer vision models relied on raw pixel data as the input to the model.To model objects more flexibly, classic computer vision models added new features derived from pixel data, such as color histograms, textures, and shapes.

2. Overview
Problem Identification
Methods Adopted
 Color Segmentation
 Morphological Processing
 Template Matching
 EigenFaces
 Gender Classification

3. Color Segmentation
Use the color information
Two approaches:
 Global threshold in HSV and YCbCr space using set
of linear equations. Lot of overlap exists
(a) (b)
Clustering in (a) YCbCr and (b) V vs. H space. Red is non-face and
blue is face data

4. Result of color segmentation using Global
thresholding

5. Second approach involves RGB vector
quantization (Linde, Buzo, Gray)
 Use RGB as a 3-D vector and quantize the RGB
space for the face and non-face regions
Overlap exists in RGB space also
Sample Blue vs Green plot for face (blue)
and non-face (red) data.

6. Results from initial quantization
 Common problems identified

7. Better Code book developed
 Problem areas broken up

8.  Initial step of open and close performed to fill
holes in faces
 Elongated objects removed by check on aspect
ratio and small areas discarded

9. Morphological Processing
Segmented and processed Image
consists of all skin regions (face, arms
and fists)
Need to identify centers of all objects,
including individual faces among
connected faces
Repeated EROSION is done with
specific structuring element

10.  Previous state stored to identify new
regions when split occurs
Superimposed mask image with eroded
regions for estimate of centroids

11. Template Matching
Data set has 145 male and 19 female faces
Need to identify region around estimated
centroids as face or non-face
Multi-resolution was attempted. But distortion
from neighboring faces gives false values
Smaller template has better result for all face
shapes
Template used is the mean face of 50x50
pixels
Mean Face used for
template matching

12. Illumination problem identified
 Top has low lighting, lower part is brighter
 Left and right edges of images do not have people
 2-D weighting function for correlation values
applied
2-D weighting function Sample correlation result

13. Result from template matching and thresholding.
Rejected - Red ‘x’. Detected Faces – Green ‘x’

14. EigenFace based detection
Decompose faces into set of basis images
Different methods of candidate face
extraction from image
EigenFaces
(a) (b)
Candidate face extraction (a) Conservative (b) multi-
resolution with side distortion

15. Sample result of eigenface. Red ‘+’ is from
morphological processing and green ‘O’ is from
eigenfaces

16. Minimum Distance between vector of
coefficients to that of the face dataset
was the metric.
It depends very much on spatial
similarity to trained dataset
Slight changes give incorrect results
Hence, only template matching was
used

17. Gender classification
 Eigenfaces and template matching for specific face features do
not yield good results
 Other features for specific females were used – the headband
 Template matching was performed for it
 Conservative estimate was done to prevent falsely identifying
males as a female
The headband template

18. Training
Image
Final
Score
Detect
Score
Number
Hits
Num
Repeat
Num
False
Positives
Distance Runtime Bonus
1 22 21 21 0 0 15.9311 71.91 1
2 22 21 23 0 2 13.6109 82.96 1
3 25 25 25 0 0 9.8625 80.48 0
4 22 22 24 0 2 11.3667 81.15 0
5 24 24 24 0 0 9.5960 69.59 0
6 23 23 23 0 0 11.5512 80.25 0
7 22 21 21 0 0 14.1537 71.52 1
Table of results for training images
Approx. 95% accuracy with about 75 seconds runtime

19. Training 1

20. Training 2

21. Training 3

22. Training 4

23. Training 5

24. Training 6

25. Training 7

26. Conclusion
RGB Vector Quantization gave excellent
segmentation
Morphological processing gave good
estimate of centroids
Template matching with illumination
correction gave near perfect results
Specific female was identified with
headband

27. Future Considerations
Edge detection to better separate the
connected faces
Preprocess the image in HSV space
before codebook comparison to improve
runtime
Improve rejection of highly correlated
non-face objects

28. Thank You
Questions ?

30. 17
16
15
14
13
12
11
10
9
8
7
2 (0)
5 (17)
6
2 (0)
6 (13)
5
2 (0)
3 (18)
4
2 (0)
3 (18)
3
2 (0)
1 (20)
2
1 (1)
2 (19)
1
Gender Recognition
Face Detection
17
16
15
14
13
12
11
10
9
8
7
2 (0)
5 (17)
6
2 (0)
6 (13)
5
2 (0)
3 (18)
4
2 (0)
3 (18)
3
2 (0)
1 (20)
2
1 (1)
2 (19)
1
Gender Recognition
Face Detection