HOW DOES FACIAL RECOGNITION TECHNOLOGY WORK?

面部识别系统如何工作

Facial recognition is increasingly used as way to access your money and your devices.

面部识别越来越多地被用来存取金钱和访问设备。

When it comes to policing, it could soon mean the difference between freedom and imprisonment.

在警务方面，它就意味着自由与禁锢的区别。

Faces can be scanned at a distance, generating a code as unique as your fingerprints.

扫描人脸生成的代码和指纹一样独特。

This is created by measuring the distance between various points, like the width of a person's nose, distance between the eyes and length of the jawline.

这是通过测量不同的点之间的距离产生的，比如一个人的鼻子的宽度，眼睛的距离和下巴的长度。

Facial recognition systems check more than 80 points of comparison, known as 'nodal points', combining them to build a person's faceprint.

面部识别系统检查80多个比较点，称为“节点”，将它们组合在一起构建一个人的面纹。

These faceprints can then be used to search through a database, matching a suspect to known offenders.

这些面纹可用来搜索数据库，将嫌犯与系统里的罪犯配对。

Facial scanning systems used on personal electronic devices function slightly differently, and vary from gadget to gadget.

在个人电子设备上使用的面部扫描系统的功能略有不同，不能设备之间都有所不同。

The iPhone X, for example, uses Face ID via a 7MP front-facing camera on the handset which has multiple components.

以iPhone X为例，iPhone X通过手机上7MP前置摄像头的多个组件来实现脸部识别。

One of these is a Dot Projector that projects more than 30,000 invisible dots onto your face to map its structure.

其中一个是点投影仪，它可以在你的脸上画出超过3万个不可见的点来映射它的结构。

The dot map is then read by an infrared camera and the structure of your face is relayed to the A11 Bionic chip in the iPhone X, where it is turned into a mathematical model.

然后用红外摄像机读取点图，你的脸的结构会被传送到iPhone X的A11仿生芯片上，在那里它被转化为一个数学模型。

The A11 chip then compares your facial structure to the facial scan stored in the iPhone X during the setup process.

然后A11芯片将你的面部结构与在安装过程中存储在iPhone X中的面部扫描进行比较。

Security cameras use artificial intelligence powered systems that can scan for faces, re-orient, skew and stretch them, before converting them to black-and-white to make facial features easier for computer algorithms to recognise.

安全摄像头使用人工智能系统，可以扫描人脸、重新定位、倾斜和拉伸，然后将它们转换成黑白图像，使电脑算法更容易识别人脸特征。

Error rates with facial recognition can be as low as 0.8 per cent. While this sounds low, in the real world that means eight in every 1,000 scans could falsely identify an innocent party..

面部识别的错误率可低至0.8%。看起来似乎很低，但在现实生活中，每扫描1000次就有可能出错8次。

One such case, reported in The Intercept, details how Steven Talley was falsely matched to security footage of a bank robber.

Intercept报道了这样一个案例，详细说明了史蒂芬·塔利是如何被错误地与银行劫犯的录像相匹配的。

According to the People's Daily Online, the technology was set up at a crossroad near Peking University Shenzhen Hospital on April 15, 2017, as part of a trial run.

据人民网报道，这项技术于2017年4月15日在北京大学深圳医院附近的一个十字路口设置，开始试运行。

The cameras operate 24 hours.

摄像机24小时运行。

A display screen was also installed at the side of the road and at the pedestrian island.

在路边和行人岛上也安装了显示屏。

Chief officer Li Qiang at Shenzhen Traffic Police Technology Department told reporters that the technology mainly relies on the camera to detect a pedestrian crossing during the red light.

深圳市交通警察局交通科技处处长李强告诉记者，这项技术主要依靠摄像头来检测闯红灯的行人。

Cameras capture an offender's face and sends it to display screens, as well as the police bureau, where using face-recognition technology is used to identify the person.

摄像头捕捉到违法者的脸，将其同时发送到显示屏及警察局，警察局通过面部识别技术来识别此人。

The monitor display operates in real-time, meaning that head-shots of any offenders will upload instantly and run on a loop.

监视器实时显示，这意味着任何违规者的头像都会立即上载并循环运行。