Scribd
Upload
13 views30 pages

Machine Learning Image Identification

The document discusses different methods for face detection and gender recognition in images, including color segmentation, morphological processing, template matching, and eigenfaces. It provides details on each method and sample results, noting that RGB vector quantization provided good segmentation while template matching with illumination correction gave accurate detection. A specific approach was used to identify females based on the presence of a headband.

Uploaded by

Dhruvee Halvadiya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
13 views30 pages

Machine Learning Image Identification

The document discusses different methods for face detection and gender recognition in images, including color segmentation, morphological processing, template matching, and eigenfaces. It provides details on each method and sample results, noting that RGB vector quantization provided good segmentation while template matching with illumination correction gave accurate detection. A specific approach was used to identify females based on the presence of a headband.

Uploaded by

Dhruvee Halvadiya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 30

Overview

Problem Identification
Methods Adopted
 Color Segmentation
 Morphological Processing
 Template Matching
 EigenFaces
 Gender Classification
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
Result of color segmentation using Global
thresholding
Overlap exists in RGB space also

Sample Blue vs Green plot for face (blue)


and non-face (red) data.

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
Results from initial quantization
 Common problems identified
Better Code book developed
 Problem areas broken up
 Initial step of open and close performed to fill
holes in faces
 Elongated objects removed by check on aspect
ratio and small areas discarded
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
 Previous state stored to identify new
regions when split occurs

Superimposed mask image with eroded


regions for estimate of centroids
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
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


Result from template matching and thresholding.
Rejected - Red ‘x’. Detected Faces – Green ‘x’
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
Sample result of eigenface. Red ‘+’ is from
morphological processing and green ‘O’ is from
eigenfaces
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
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


Table of results for training images

Training Final Detect Number Num Num Distance Runtime Bonus


Image Score Score Hits Repeat False
Positives

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

Approx. 95% accuracy with about 75 seconds runtime


Training 1
Training 2
Training 3
Training 4
Training 5
Training 6
Training 7
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
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
Thank You
Questions ?
Face Detection Gender Recognition
1 2 (19) 1 (1)
2 1 (20) 2 (0)
3 3 (18) 2 (0)
4 3 (18) 2 (0)
5 6 (13) 2 (0)
6 5 (17) 2 (0)
7
8
9
10
11
12
13
14
15
16
17

You might also like