Eigenface Algorithm Results Summary

Image Pre-processing

We present a range of pre-processing techniques, which may affect the EER of the eigenface system, when applied to face images prior to recognition.  The image processing methods fall into four main categories: colour normalisation methods, statistical methods, convolution methods and combinations of these methods.  The methods are used to produce a single scalar value for each pixel.  Examples of these pre-processing methods can be seen below.

---

Equal Error Rates

We present the results produced by using various image processing methods as a bar chart of EERs.  The base-line eigenface system (no image processing) is displayed in the chart as a dark red bar.  It can be seen that the majority of image processing methods did produce some improvement to the eigenface system.  However, what is surprising is the large increase in error rate produced by some of the colour normalisation methods of image processing.  An increase is also witnessed using the blurring filters.  It is therefore not surprising to see that the edge enhancing methods had a positive impact on the EERs (the find edges and contour filters were particularly effective), as did the statistical methods.

---

Tweaking

Having identified the most successful image processing method of those evaluated (Local Brightness Contour), we continue to improve the system by testing different cropping of images to find the optimum for this image processing method, reaching an EER of 22.4%.