EVERY day more than 8,000 containers flow through the Port of Rotterdam. But only a fraction are selected to pass through a giant x-ray machine to check for illicit contents. The machine, made by Rapiscan, an American firm, can capture images as the containers move along a track at 15kph (9.3mph). But it takes time for a human to inspect each scan for anything suspicious—and in particular for small metallic objects that might be weapons. (Imagine searching an image of a room three metres by 14 metres crammed to the ceiling with goods.) To increase this inspection rate would require a small army of people.

荷兰鹿特丹港（Port of Rotterdam）每日装卸的集装箱超过8000个。不过，只有一小部分集装箱会挑出来，通过一个巨大的X光安检仪，接受非法物品检查。这个仪器由美国安检设备供应商 Rapiscan生产，对在履带上以每小时15公里的速度移动的集装箱抓取影像。可是，对于工作人员来说，要检查每一幅画面，甄别出可疑物品，尤其是疑似是武器的小型金属物品，需要花费相当多的时间。（想像一下，在一间宽3米长14米、塞满物品的房间内进行搜寻）为提高检测率，则需要一定人手。

A group of computer scientists at University College London (UCL), led by Lewis Griffin, may soon speed up the process by employing artificial intelligence. Dr Griffin is being sponsored by Rapiscan to create software that uses machine-learning techniques to scan the x-ray images. Thomas Rogers, a member of the UCL team, estimates that it takes a human operator about ten minutes to examine each X-ray. The UCL system can do it in 3.5 seconds.

伦敦大学学院的一组由刘易斯·格里芬（Lewis Griffin）带领的计算机科学家采取人工智能技术，或很快能提升检测速度。Rapiscan公司正在资助赞助格里芬博士开发一种软件，通过机器学习技术来扫描X光图像。该小组成员托马斯·罗杰斯（Thomas Rogers）表示，一名安检员检查一张X光图像大约需要10分钟。而他们开发的这个系统只需3.5秒。

Dr Griffin’s team trained its system on hundreds of thousands of container scans provided by Rapiscan. The scans were missing concealed metallic objects that might pose a threat, so the UCL team took a separate database of x-rayed weapons and hid them in the container images. A paper the group presented at the Imaging for Crime Detection and Prevention conference in Madrid last week showed that in tests, the system spotted nine out of ten hidden metallic objects. Only six in every hundred readings flagged a weapon when there was nothing. Dr Griffin says this false positive rate has been reduced to one in every 200 since the paper was written in August. The group’s software has also been trained to detect concealed cars.

格里芬博士通过Rapiscan公司提供的数十万集装箱扫描图像训练这个系统。传统的扫描仪无法识别出具有潜在危险的隐蔽金属物体，因此，研究小组另建了一个有武器的X光图像的数据库，并将这些数据混入在集装箱图像中。11月在西班牙马德里举行的犯罪侦查与预防图像国际会议（ Imaging for Crime Detection and Prevention conference ）中，该研究小组提供的报告显示，他们的系统在测试过程中检测出隐蔽金属物体的概率达到十分之九。只存在6%的失误率。格里芬博士表示，从8月报告完成后，现在该系统的误报率已降低到0.5%。该小组的软件也用于训练软件监测隐蔽的汽车。

The UCL team hopes to test its software shortly on real containers, some with small weapons deliberately hidden inside. Assuming that works, Dr Griffin plans to integrate the artificial-intelligence system into Rapiscan’s scanning systems over the next few months. The team is also aiming to train the system to detect “anomalies”—the machine-learning equivalent of a human hunch that something is not quite right about a scan. That could, for instance, be something unusual in the way things are positioned inside the container. Given enough data, the scientists reckon computers can train themselves to identify discrepancies like this.

UCL团队的科学家们希望可以尽快对真正的集装箱进行软件测试，并在特意在集装箱内隐藏一些小型武器。格里芬博士认为软件能通过测试，并计划在接下来的几个月中，将他们的这个人工智能系统同Rapiscan的扫描系统结合在一起。此外，研究小组还致力于训练该系统监测异常情况，这是一种类似于人类的直觉的机器学习能力，可以判断出扫描图像不太正常的情况。例如，集装箱内物品摆放的方式不寻常。研究了大量数据以后，科学家们认为计算机可通过自我训练识别出上述这种异常情况。

It is not just in ports where machine learning could speed up scanning. Weary travellers dragging themselves through the slow crawl of airport security could also benefit. Suitcases are smaller than containers, and their contents are more predictable, so humans are able to inspect their X-rays quickly and thoroughly (although regular rest breaks are still needed).

使用机器学习来加快安检速度的方式并不只是适用于港口。在机场，旅客们也总是要拖着疲惫的身躯在安检处缓慢的人流中踱步，若有这种技术，也会相当受益。行李箱要比集装箱小很多，而且里面所装的物品也更容易预测，因此，工作人员在检查行李箱的X光图像时也更快更彻底（当然还要有定期休息时间）。

Toby Breckon of Durham University is working on automated x-ray analysis to detect small items of the sort that might be contained in passengers’ cabin and hold bags. He says his group has already had an algorithm installed in commercial scanning systems. Dr Breckon thinks intelligent scanning systems will at first operate in the background at airports, for instance rechecking bags in case human inspectors have missed something. They might also be used to flag bags that could be worth a manual inspection.

目前，英国杜伦大学（Durham University）的托比·布雷肯（Toby Breckon）博士在研发一种X光自动分析系统，用来检测可放置进客舱和随身行李内的小型物品。布雷肯博士表示，他的团队已开发出一种可安装于商用扫描系统的算法。他认为，智能扫描系统首先会应用于机场，为防止人工安检员有所遗漏，可用于行李的二次检查。智能系统还可以用于标记需要人工检查的手提包。

In time, however, automated screening systems may go from being useful tools for human operators to outperforming them. If his team can get its hands on the large amounts of security imagery it needs to feed into its software, Dr Griffin thinks container scanning, at least, might be entirely automated. Perhaps bag-scanning at airports might go the same way. But there will still be a need for people. Someone has to be around to check inside containers and bags with suspicious contents.

早晚有一天，自动扫描系统会从有效辅佐安检员变成优于安检员。格里芬博士认为，如果他的团队可以获得大量安检影像，用于训练自己的软件，那么至少可以实现集装箱扫描全程自动化。或许机场的行李扫描系统也可同样实现自动化。但是，即便如此，还是不能彻底脱离人工安检。无论是集装箱还是手提包内的可疑物品检测，依然需要人工安检。

编译：高艺宸

审校：张雨珊

编辑：翻吧君

英文来源：经济学人