Yes, most KFC and McDonald's have started to pay by brushing their faces.

AliPay: version 11.2.36.8111

In our life, many places like KFC and McDonald's are already using Alipay to pay by brushing their faces. I also went to feel it. I really don't need a mobile phone, and eating depends on my face. While using face payment, we will certainly worry about whether "face-brushing payment" is really safe and whether face recognition is accurate enough.

for our users, it is more convenient and faster to pay by face recognition than by mobile phone. Face payment no longer depends on hardware devices such as mobile phones, and it also saves people the trouble of remembering and inputting passwords. Even if the mobile phone is dead and the indoor signal is not good, you can recognize the face in person, and you can easily get all the payment processes in just a few seconds.

The process of face recognition payment is as follows:

Take Alipay as an example, Alipay: version 11.2.36.8111

Step 1: Face positioning detection: the system recognizes whether a face is close to it and accurately locates the face position.

Step 2: Face image preprocessing: The machine adjusts the recognized face to the standard position and size, and preprocesses the face image with illumination compensation and filters, so as to extract face information in the next step.

Step 3: facial feature extraction: use the algorithm to extract everyone's face information to get everyone's "unique" face information.

Step 4: Identify and output: Compare the detected face with the existing information in the system, and the consumer face information is also associated with the payment system. After the consumer's identity information is displayed, he/she only needs to click "OK" on the touch screen to confirm, and the whole transaction process is completed

:

The face unlocking technology used in face recognition payment adopts 3D structured light technology, and the whole system of 3D structured light includes structured light projection equipment, camera and image acquisition and processing system. The process is that the projection equipment emits light to the measured object, the camera shoots the three-dimensional light pattern formed on the measured object, and the photographed image is processed by the acquisition and processing system to obtain the surface data of the measured object, and then the data is compared with the database, and the similarity is set to a value to determine whether it is the person. In order to enhance the recognition reliability, the currently used face recognition technologies generally include face world model, blink detection, nodding and turning, etc., with high accuracy.

At present, the factors that restrict the development of face recognition payment mainly focus on the dynamic accuracy of collected information and the speed of calculating information feedback after collection. However, due to the high application security requirements of the payment link, the more complicated offline scene, the greater challenges of open environment and public equipment, large-scale commercialization is still in its infancy.