Gender recognition from frontal facial images within project FP7-ICT-247525-HUMAVIPS

NEW - Structural model - extension on aspect ratio

<< zpět

Overview

This experiment extends earlier experiment 05i on the aspect ratio. Because we need to know aspect ratio of training samples we use a little bit modified dataset. So we compute again validation error of previous model 05i.

Choosed values of window aspect ratios are given by statistical measurement from training dataset.

Results

Parameters of experiment
imSize [h x w]80 x 64
winSize [h x w]60 x 40
window positionhalf in either axis
window rotation{-pi/30; -pi/60 0; pi/60; pi/30}
window scale{0.8 1 0.9}
window ratios *
* only for new model
{1.35 1.5 1.65}


OLD EXPERIMENT 05iNEW EXPERIMENT 05r
LAMBDATraining errorValidation errornIterations Training errorValidation errornIterations
1%14.36%33 4.89%12.76%36
0.10.02%10.72%128 0.02%10.00%129
Testing error for minimal validation error: 12.49%

Distribution of aspect ratios through testing dataset

Aspect ratioCount
1.35643
1.53545
1.65905

Graphical results

In figure 1 you can see twelve random selected samples, detections on whole database are available in file detection.zip

Figure 1: Random samples from dataset that haven't basic aspect ratio 1.5 .. also in MATLAB figure

References

Choon Hui Teo , S.V.N. Vishwanthan , Alex J. Smola , Quoc V. Le: Bundle Methods for Regularized Risk Minimization, The Journal of Machine Learning Research, 11, p.311-365, 3/1/2010
<< zpět