Face recognition technology may detect
It’s critical to security to identify people accurately (and not embarrass yourself by embracing strangers). It has been presented as a primary justification for banning and regulating those who wear religious headscarves and face coverings in public.
A plan to force Muslim women who wear face coverings or the niqab to sit in glass enclosures in Parliament has been scrapped, but the problem remains: How good are we at recognizing people based on their facial features?
Face recognition systems use computer algorithms to recognize specific aspects of a person’s face. The data is then translated into a mathematical representation and compared to data from other faces in the face recognition database. These features include the distance between the eyes and the curve of the chin.
Facial recognition technology is rapidly developing and is being used in a variety of industries such as marketing, education, criminal investigation, security and biometrics. It can now assess an individual’s facial expressions as well as recognize them. A study published in the International Journal of Computer Vision focuses on the limitations of facial recognition software when a person’s face is partially obscured, as might occur while wearing a hijab or protective face mask.
A great deal of study has been devoted to whole-face biometric identification. However, using faces that appear only partially, such as veiled people, is difficult. In this study, a deep convolutional neural network (CNN) is used to extract properties from images of veiled faces.
DeepVeil, the team’s proof of concept, used close-up portraits of hijabi people in conjunction with an internal image database. The next step will involve working with a more diverse set of images collected in different conditions, including images taken from different angles. However, with the development of algorithms and software, a clean face-to-face image is no longer needed to identify a person, as was the case in the early days of a standard facial recognition system. As a result, DeepVeil may go through the same with the right approach and continuous development.
Face identification and characteristics
Coverings that conceal the majority of the face, such as the burqa, will make identification difficult. However, coverings such as a veil or veil tend to hide external features such as the shape of the face, ears, and hairline.
The subjects’ ability to identify two facial images when only internal facial characteristics were displayed, as in these images, was compared with all features revealed in the studies. The results indicate that if only internal data is present, recognition accuracy improves; However, the presence of external features may impair identification. To make identification easier, we should probably all wear a headscarf.
The external aspects of the face, in particular the hairline, can be modified quickly and therefore may not serve as a reliable basis for identification. Importantly, a new study revealed that faces that wear a headscarf are perceived as more similar than those that don’t. This means that the veil affects people’s impressions of faces even when they are asked to focus only on the inner aspects of the face.
Differences in face recognition across cultures
Researchers Ahmed Mageria and Marcus Bendmann have discovered discrepancies in performance between Westerners (British University students) and people from Middle Eastern cultures (look at the Egyptians). People from cultures where headscarves are common did better at identifying people with and without head coverings.
This effect has been linked to the transracial effect, in which people get to know people of their race better. Both effects show that our experiences have a significant impact on our sense of identity. The results of this study show that we may be able to improve our ability to recognize people based on their faces. The hard part is deciding how.
Other factors have a greater influence
What about severe changes in appearance caused by aging, weight loss or gain, or plastic surgery?
Age-related changes in facial appearance are particularly difficult to determine. Children who are in custody or who are missing may not be easily discovered by the authorities because the photos rarely match their appearance.
Despite common images of forensic artists making “old” images suitable for identification, relatively little scientific study has been done on the accuracy of this identification and other types of image-based identification. At present, the study of the effects of aging on identification accuracy is a major focus. Passport officials are taught to look for weight loss or growth, as well as plastic surgery, as potential sources of identity errors. However, we lack the data to determine if this training was successful.
Beyond facial recognition technology that can be seen through the niqab! Privacy breach? first appeared.
#Face #recognition #technology #niqab #Privacy #breach