VOA慢速英语(翻译+字幕+讲解):研究称戴口罩面部识别的准确率有所提高
日期:2020-12-03 15:42

(单词翻译:单击)

*Pa|@y93YKyMK,E;+5C~vftHN;

听力文本

xSK|d&d1Gl2Ukqh!

Study: Facial Recognition Is Getting Better at Identifying People in Masks
A U.S. government study has found that facial recognition technology is getting better at identifying people wearing masks.
The study is part of ongoing research by the U.S. Commerce Department's National Institute of Standards and Technology (NIST). The agency has examined the effectiveness of more than 150 facial recognition systems on people wearing face coverings. The systems are powered by machine learning algorithms.
The first results of the study were announced in July, as health officials across the world urged people to wear masks to limit the spread of the coronavirus. New findings were released this week.
Police agencies around the world have long used facial recognition technology to search for and help catch people accused of crimes.
It can also be used to unlock phones or other electronic devices, and in some cases, even vehicles. Some robots use facial recognition technology to recognize the people they are communicating with.
However, the wide use of masks in public has created major difficulties for such systems.
The study looked at facial recognition systems already in use before the pandemic. It also looked at systems specially developed to work on masked faces. Developers of the technology voluntarily provide their algorithms for testing.
The NIST said it processed a total of 6.2 million images for the experiment. These included pictures provided by individuals seeking U.S. immigration benefits, as well as images from border crossings of travelers entering the United States.
People in the images were not actually wearing masks. So, the researchers digitally added different mask shapes to faces in the pictures for use in the study. In some cases, up to 70 percent of a person's face was covered in the images.
Overall, the NIST said its research shows that the top-performing facial recognition systems fail to correctly identify unmasked individuals about 0.3 percent of the time. The failure rate rose to about 5 percent with masked images tested with the most effective systems. Many of the lower performing algorithms, however, had much higher error rates with masked images — as high as 20 to 50 percent.

WK)QPsw2IZIcXdJwYG

口罩对面部识别软件的影响.jpg
In the latest findings, researchers included results from 65 new facial recognition systems that have been developed since the start of the pandemic. Some of these systems performed "significantly better" than the earlier ones, the NIST's Mei Ngan said in a statement on Tuesday. She is a lead researcher on the project.
"In the best cases, software algorithms are making errors between 2.4 and 5 percent of the time on masked faces," Ngan said. She added that this performance rate is "comparable to where the technology was in 2017 on non-masked photos."
The researchers reported that the systems were much more effective at identifying individuals when one image of the person was masked and the other was unmasked. When faces were covered in both photos, failure rates rose greatly.
Not surprisingly, the study found that round-shaped masks — which cover only the mouth and nose — led to fewer errors than wider ones that stretch across the cheeks. Also, masks covering the nose led to higher failure rates than those that did not.
The new study also ran tests to see whether different colored masks would affect error rates. The team used red, white, black and light blue. The research findings suggested that generally, the red and black masks led to higher failure rates than the other colors.
I'm Bryan Lynn.
The new study also ran tests to see whether different colored masks would affect error rates. The team used red, white, black and light blue. The research findings suggested that generally, the red and black masks led to higher failure rates than the other colors.

KUJ7=L!f],;VVILs

+YfCEXOh]dO

重点解析

UdfuXmqo5Gf3D]Y3

7fw^u(p9CH.QbPr

重点讲解:
1. search for 搜寻;搜索;搜查;寻求;
You can use a directory service to search for people on the Internet.
你可以利用因特网的目录服务搜索人名SOyf](Xqg-fI
2. in use 在使用;
The table folds up when not in use.
这桌子不用时可以折叠起来Xu%Yck|m*SP!RAm]kEJ(
3. a total of 总共;总计;
The companies have a total of 1,776 employees.
这些公司总计有1,776名员工Y~~C7;wlGr,]bX4wTqj
4. be comparable to 类似的;可比较的;
This broad and deep tragic consciousness is comparable to and is not in the least inferior to the ancient Greek tragedies.
这种深广的悲剧意识,完全可以和古希腊悲剧相提并论而无愧色=1.vn[Q!zETek

%V383qbIGe3x_

参考译文

[,km%PaaXN

研究称戴口罩面部识别的准确率有所提高
美国政府的一项研究发现,面部识别技术在识别佩戴口罩者方面越来越出色Qqy4M-vL^Go)+,
这项研究是美国商务部分支机构美国国家标准与技术研究所(简称NIST)正在进行的研究的一部分cqbdqGAgdhQR。该机构检查了150多个面部识别系统识别佩戴口罩者的有效性^_rCj~F&U[xGxWvqULC。这些系统由机器学习算法驱动WPqj7Hwod5
这项研究的首批结果于今年7月公布,当时世界各地的卫生官员都在敦促人们佩戴口罩,以限制冠状病毒的传播.;HBhn|4,&BF。最新研究结果于本周公布d]K*C3(fSfyZ
长期以来,世界各地的警察机构都使用面部识别技术来搜索和协助抓捕被指控犯罪的人^4[)j)*!q56n940JJ
该技术还可以用来解锁电话或其他电子设备,在某些情况下,甚至能解锁车辆WA+K+|y9POHuq。有些机器人使用面部识别技术来识别与他们交流的人yhiS76zxaEUiI
然而,口罩在公共场合的广泛使用给这类系统带来了很大的困难!8eEI95B5DJU876xzE
这项研究着眼于大流行前已经使用的面部识别系统RcWXLa*7%6OP*W#r。它还研究了专门为处理戴口罩面孔而开发的系统]vW|(lR|sWu@。该技术的开发人员自愿提供他们的算法进行测试.ztVd=^22Q8Q
美国国家标准与技术研究所表示,他们在测试中总共处理了620万张照片-t6mO;Rq-GML。这些照片包括寻求美国移民福利者提供的照片,以及旅客入境美国时在过境点提供的照片=o&XF&d(Hq%tr^1
照片中的人实际上并没有戴口罩Cmt^rPzpn~j%s%。因此,研究人员用数字技术在照片中的脸上添加了不同的形状的口罩,以供研究使用n002O=eDDFn**。在某些情况下,一个人脸部的70%被图像覆盖*mL0PxBl*~I
美国国家标准与技术研究所表示,总的来说,他们的研究表明,性能最好的面部识别系统识别未戴口罩个人的失败率约为0.3%.s|%Pk+ZlHVA2f=o。而最有效系统识别戴口罩照片时的失败率上升到5%左右#x[6.1VwC|。然而,许多性能较低的算法在识别戴口罩图像时的错误率还要高得多——高达20%到50%iF*i(%3E5|jq
在最新的研究结果中,研究人员纳入了65种新面部识别系统的结果,这些系统在大流行爆发后开发=~FbW#eFh6Lg7mN。美国国家标准与技术研究所的Mei Ngan在周二的一份声明中表示,其中一些系统的性能相比之前“明显好了很多”j*!YV.MF38K,r[C。她是这个项目的首席研究员R;xt!M).RAgXX
Ngan表示:“在最好的情况下,软件算法识别戴口罩面孔时的错误率在2.4%到5%之间l|R3Vt3o)5vz4WqG.;。”她补充说,这一性能比率“与2017年该技术识别未戴口罩照片时的表现不相上下xrl.hlRSBuvlQr_。”
研究人员报告称,在一个人的一张照片佩戴口罩,而另一张照片未佩戴口罩时,这种系统在识别个体方面更加有效4lVra~WK%y[qx(%^f。当两张照片都佩戴口罩时,失败率则大大上升%xrB6@&A4C
毫不奇怪,这项研究发现,相比覆盖整个脸颊的宽大口罩,圆形口罩(只覆盖嘴和鼻子)导致的错误更少|c^i(csO(+zn#ZVRKG。此外,相比不戴口罩,遮住鼻子的口罩的失败率更高Qrk;@p~P~%8I!ku.9Gs
这项新研究还就不同颜色的口罩是否会影响错误率进行了测试vlcT5]uWB]K9i%72a。研究团队测试了用红色、白色、黑色和浅蓝色口罩Q[RYzy,#y7q~#V2|v7(。研究结果表明,一般来说,相比其他颜色的口罩,红色口罩和黑色口罩导致的失败率更高#qRty[dE]nrIe.mNyk
布莱恩·林恩报道&rWMbyO8#V=JEl

Xk#sL0dnbkpCv(.K]

译文为可可英语翻译,未经授权请勿转载!

*U82e,oGHDF#C=nBgJl^UvJo4mzk+P%eBEK1#OnrB
分享到