Florida Atlantic University engineers in Boca Raton are working on a superior new face recognition technique that can see through disguises.
Lin Huang, from the university's department of engineering, says that every face has special features that define people, yet faces can also be very similar.
The researcher adds that this is what makes computerised face recognition for security and other applications an interesting, but difficult, task.
Face recognition software has been in development for many years, but the main technical limitation is that, although the systems are accurate, they require a lot of computer power.
Early face recognition systems simply marked major facial features -- eyes, nose mouth -- on a photograph, and computed the distances from these features to a common reference point.
In the new study, Huang and colleagues Hanqi Zhuang and Salvatore Morgera have applied a one-dimensional filter to the two-dimensional data from conventional analyses, such as the Gabor method (which is based on neural networks).
This allows them to reduce significantly the amount of computer power required without compromising accuracy.
The team tested the performance of their new algorithm on a standard database of 400 images of 40 subjects. Images are grey scale and just 92 x 112 pixels in size.
They found that their technique was not only faster and worked with low resolution images, such as those produced by standard CCTV cameras, but it also solved the variation problems caused by different light levels and shadows, viewing direction, pose, and facial expressions.
It could even see through certain types of disguises, such as facial hair and glasses.
The findings have been published in International Journal of Intelligent Systems Technologies and Applications.
