Stellenbosch University (South Africa) Alex Muthua wants to help improve facial recognition technology
Facial recognition technology is used in many different areas – from airports, retail stores, healthcare, law enforcement, and marketing to banks – to identify people through images and videos of their faces. However, a drawback of this technology is that it does not accurately recognize the faces of people with highly pigmented skin tones.
“One way to enhance the facial recognition of people with darker skin is to incorporate the portion of the infrared spectrum (the near-infrared part) that electronic sensors can perceive,” says Alex Muthua, who received his Master’s degree in Electronic and Electrical Engineering on Wednesday (7 December 2022) at Stellenbosch University’s December graduation.
As part of his study, Muthua explored how infrared light could help to improve the facial recognition of people with a highly pigmented skin tone.
“Individuals with highly pigmented skin appear darker in visible light images, which means that there is less light information available in the image on which to perform facial recognition. By adding infrared, one can increase the dynamic range of the intensity values, which in turn aids the face recognition system.”
According to Muthu, most digital cameras have a filter that blocks out the infrared light needed for this facial recognition. Using a camera with the filter already removed, Muthua took 9 000 images of 500 individuals with highly pigmented skin in different light spectra – visible, near-infrared, and a combination of the two (full-spectrum).
This way, he could augment existing datasets with images of highly pigmented individuals. Muthu points out that there is typically a bias in these datasets, with more photos of light skin pigmentation represented than darker skin pigmentation. These datasets also don’t contain infrared images.
He also assessed the impact of narrow and wide cropping, different facial orientations, and sunlight and shaded conditions.
“We found that using infrared light, the faces of people with a highly pigmented skin tone could be recognised with greater accuracy than using only visible light,” says Muthu.
He also fine-tuned an existing face recognition algorithm. He inspected the activation maps of an available convolutional neural network, a machine-learning architecture used primarily for image processing. This was done to determine the essential features of facial recognition for people with highly pigmented skin.
“We found that the nose area appears to be the most important feature for facial recognition compared to the chin and forehead.”
Muthu says as face recognition technology continues to grow, its performance must be improved because any bias or disparity may be detrimental to its advancement and potential use.