考研英文原刊《经济学人》识别人们的行踪

上传人:tian****1990 文档编号:72930182 上传时间:2019-01-24 格式:DOC 页数:3 大小:68.68KB
返回 下载 相关 举报
考研英文原刊《经济学人》识别人们的行踪_第1页
第1页 / 共3页
考研英文原刊《经济学人》识别人们的行踪_第2页
第2页 / 共3页
考研英文原刊《经济学人》识别人们的行踪_第3页
第3页 / 共3页
亲,该文档总共3页,全部预览完了,如果喜欢就下载吧!
资源描述

《考研英文原刊《经济学人》识别人们的行踪》由会员分享,可在线阅读,更多相关《考研英文原刊《经济学人》识别人们的行踪(3页珍藏版)》请在金锄头文库上搜索。

1、凯程考研辅导班,中国最强的考研辅导机构,http:/ 考研就找凯程考研,学生满意,家长放心,社会认可!2015考研英文原刊经济学人:识别人们的行踪Facial-recognition systems are getting better面部识别系统愈发完善WITH some pride, the FBI trumpeted the news last month that thanks to the agencys facial-recognition system Neil Stammer, wanted for sexual assault and kidnapping, had been

2、apprehended in Nepal after being on the run for 14 years. The truth was slightly moreprosaic. A State Department official had used the FBIs “Wanted” posters in a test for passportfraud. The system then matched Mr Stammers face with an American calling himself KevinHodges who regularly visited the US

3、 embassy in Kathmandu to renew his visa. Still, MrStammers arrest illuminates the growing importance of facial-recognition technology.上个月,在FBI面部识别系统的帮助下,因性侵犯和绑架而被通缉长达14年的Neil Stammer在尼泊尔落入法网。FBI对此大肆宣传,还带着点小骄傲呢 经过可能较为平淡。一名国务院官员使用FBI的通缉海报来测试护照欺诈行为。然后系统识别出,Stammer的面部同一名自称Kevin Hodges的美国人相符。后者经常到美国驻加德满都

4、大使馆去更新他的签证。不过,Stammer的落网,说明面部识别技术日益重要。The two main techniques used to recognise faces electronically are principal-componentanalysis (PCA) and linear-discriminant analysis (LDA). Both compare a picture of someonesphizog with a reference image taken in a controlled environment. Passport photos andmug

5、shots, then, are about as ideal as it gets.电子识别人脸的两种技术分别为主成分分析(PCA)和线性判别分析(LDA)。两种方法都是通过在特定环境下比较某人的面部和参照图片。碰巧,护照照片和疑犯照片是最理想化的。Basic PCA and LDA are good for skin colour, hair colour and the like. Advanced systems, suchas that used with British biometric passports, may look at cheek bones, the bridge

6、 of the nose,jaw lines and eyes.基本的PCA和LDA擅长处理肤色、发色等。先进系统,比如英国计量生物学护照所采用的,可能会记录面颊骨骼,鼻梁,下颌轮廓以及眼睛。All of which is fine when someone is sitting or standing in front of a camera, but is less useful inthe world beyond the studio. That requires a technique called Elastic Bunch Graph Matching(EBGM), which

7、tries to create a three-dimensional (3D) model from two-dimensional images.This model can, thereafter, be used to match any subsequent image, or part thereof.在人正坐在或者正立在摄像头前的时候,所有这些标准都好办,但是在摄影棚外就不那么有用了。这要求一种名为弹性束图匹配(EBGM)的技术,该技术力求通过2D图像创建一个3D模型。因此这个模型就能用于匹配任何相关图片,或其中的部分。EBGM considers the head as a u

8、nion of two ellipsoids: one whose main axis is vertical, andruns from forehead to chin; the other whose main axis is horizontal, and runs from tip of thenose to the back of the cranium. This basic scheme is overlaid with “fiducial” points which act asanchors for the modelling. These can be as few as

9、 half a dozen (the pupils of the eyes, thecorners of the mouth, and so on), or as many, in one system, as 40,000.EBGM将头部视为两个椭圆的结合体。一个的主轴是垂直的,从前额到下巴;另一个的主轴是水平的,从鼻尖到头盖骨后侧。基本方案是通过确定基点位置,定位模型尺寸。基点少则6个(瞳孔,嘴角,等等),多则可能在一个系统中达到40000个。EBGM allows the construction of a three-dimensional representation of a fa

10、ce from poorly litimages taken at odd angles, such as a closed-circuit television camera might provide. Once itrecognises enough fiducial points it can work out what aspect of a face it is viewing. It thenextrapolates the expected positions of other fiducial points. As more data come in from thecame

11、ra, the models shape is updated. Given enough horsepower, says a British official, such asystem can build a model from as few as 80 pixels located between a subjects eyesand onlytwo images are needed for a 3D reconstruction.EBGM可以将小角度拍摄的暗光照片,比如闭路电视所提供的,塑造为三维模型。一旦它捕捉到了足够的基点,系统就能计算出它所观测的是面部的那个位置。然后系统推

12、断出其他基点的预期位置。随着摄像头提供的数据增多,模型的形状不断更新。如果有足够动力,比如英国官方要求,只需要两张照片,像素少到在人物的眼睛中只有80个像素,这个系统就能偶建立出3D复原模型。Governments are not the only ones interested. Earlier this year, Facebooks DeepFace systemwas asked whether thousands of pairs of photos were of the same person. It answeredcorrectly 97.25% of the time, a

13、 shade behind humans at 97.53%. Although DeepFace is only aresearch project, and is aided by the fact that many Facebook photos are tagged with thenames of people in the images, which lets the system learn those faces in different poses andlighting conditions, it is still an impressive feat.并不只有政府对此

14、感兴趣。今年早些时候,有人拿脸谱的“深脸”系统测试了成千上万张照片,看他们是否是同一个人。其正确率为97.25%,在人背后后有阴影的情况下识别率为97.53%。尽管深脸只是研究项目,并且脸谱上的许多照片都是贴着人的姓名这个情况给出了一定帮助,使得系统能够辨别出不同姿势、不同采光下的人脸,但是这个成果仍旧令人瞩目。As DeepFace shows, access to an accurate gallery of images is crucial. Passport photos, orthose on national identity cards, can act as such gal

15、leries, as they can be rendered by EBGMinto usable 3D models. Add in the increasing ubiquity of closed-circuit television, and the ideathat anyone will be able hide for long in Nepal, or anywhere else, looks quaint.正如深脸所显示的,想精确识别大批量图案依然困难重重。护照照片,或者那些用在国民身份证上的,可以作为这种相片管理系统,因为他们可以可以由EBGM转述为实用3D模型。再考虑到

16、闭路电视的普及,那么任何一个人,想要在尼泊尔或者其他任何地方藏起来的这种想法都会变得不切实际。凯程教育:凯程考研成立于2005年,国内首家全日制集训机构考研,一直从事高端全日制辅导,由李海洋教授、张鑫教授、卢营教授、王洋教授、杨武金教授、张释然教授、索玉柱教授、方浩教授等一批高级考研教研队伍组成,为学员全程高质量授课、答疑、测试、督导、报考指导、方法指导、联系导师、复试等全方位的考研服务。凯程考研的宗旨:让学习成为一种习惯;凯程考研的价值观口号:凯旋归来,前程万里;信念:让每个学员都有好最好的归宿;使命:完善全新的教育模式,做中国最专业的考研辅导机构;激情:永不言弃,乐观向上;敬业:以专业的态度做非凡的事业;服务:以学员的前途为已任,为学员提供高效、专业的服务,团队合作,为学员服务,为学员引路。如何选择考研辅导

展开阅读全文
相关资源
相关搜索

当前位置:首页 > 办公文档 > 其它办公文档

电脑版 |金锄头文库版权所有
经营许可证:蜀ICP备13022795号 | 川公网安备 51140202000112号