Researchers have developed software that can solve masks, one of the biggest problems of facial recognition systems. The system can perform biometric identification even when masks are present.
With the development of artificial intelligence facial recognition systems has reached very advanced levels. However, it still has some flaws. Especially during the COVID pandemic, the masks we wore on our faces were disrupting facial recognition technologies. Although the number of people wearing masks has decreased, work on this problem continued.
Researchers from Chlef Hassiba Benbouali University in Algeria, Able to recognize faces even when masks are present developed a software. The study was published via Inderscience.
Trained with a huge database of images of individuals wearing masks
The researchers trained the system they developed using a large database of photographs of individuals in various poses and expressions. Masks were also placed on the faces of these individuals. It was stated that the main purpose of the study was to facilitate biometric identification in scenarios where wearing a mask has become the norm.
The database in question is where the masks we all once wore are placed. 18 thousand masked faces And 2 thousand unmasked human faces It contained. The software uses artificial intelligence, a subset of artificial intelligence that enables analysis of visual information, to overcome the difficulty of recognizing faces hidden by masks. from convolutional neural networks (CNN) benefited. As a result of tests conducted on more than one CNN model, ResNet 18 It has been observed that a model called Masked Faces can detect masked faces most accurately and effectively.
As it is known, facial recognition systems can be used in many different areas, from unlocking phones to detecting criminals. Researchers also say that the technology they developed can be integrated into these areas and be very useful in cases of mask use.
RELATED NEWS
Microsoft Developed a Special Artificial Intelligence Model for US Spies: It Works Without Internet!
However, despite the promising results, the limitations of the system and how it will perform in practice are unclear. Additionally, although ResNet 18 is successful, it is unknown whether this model will overcome difficulties in different situations, such as different lighting conditions or changing mask types. So very to further research there is need.