評論
打印
Science and technology
科學(xué)技術(shù)
Biometrics
計量測定學(xué)
Clocking people's clocks
識別人們的行蹤
Facial-recognition systems are getting better
面部識別系統(tǒng)愈發(fā)完善
WITH some pride, the FBI trumpeted the news last month that thanks to the agency's facial-recognition system Neil Stammer, wanted for sexual assault and kidnapping, had been apprehended in Nepal after being on the run for 14 years. The truth was slightly more prosaic. A State Department official had used the FBI's “Wanted” posters in a test for passport fraud. The system then matched Mr Stammer's face with an American calling himself Kevin Hodges who regularly visited the US embassy in Kathmandu to renew his visa. Still, Mr Stammer's arrest illuminates the growing importance of facial-recognition technology.
上個月，在FBI面部識別系統(tǒng)的幫助下，因性侵犯和綁架而被通緝長達(dá)14年的Neil Stammer在尼泊爾落入法網(wǎng)。FBI對此大肆宣傳，還帶著點小驕傲呢~ 經(jīng)過可能較為平淡。一名國務(wù)院官員使用FBI的通緝海報來測試護照欺詐行為。然后系統(tǒng)識別出，Stammer的面部同一名自稱Kevin Hodges的美國人相符。后者經(jīng)常到美國駐加德滿都大使館去更新他的簽證。不過，Stammer的落網(wǎng)，說明面部識別技術(shù)日益重要。
The two main techniques used to recognise faces electronically are principal-component analysis (PCA) and linear-discriminant analysis (LDA). Both compare a picture of someone's phizog with a reference image taken in a controlled environment. Passport photos and mugshots, then, are about as ideal as it gets.
電子識別人臉的兩種技術(shù)分別為主成分分析（PCA）和線性判別分析（LDA）。兩種方法都是通過在特定環(huán)境下比較某人的面部和參照圖片。碰巧，護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, such as that used with British biometric passports, may look at cheek bones, the bridge of the nose, jaw lines and eyes.
基本的PCA和LDA擅長處理膚色、發(fā)色等。先進系統(tǒng)，比如英國計量生物學(xué)護照所采用的，可能會記錄面頰骨骼，鼻梁，下頜輪廓以及眼睛。
All of which is fine when someone is sitting or standing in front of a camera, but is less useful in the world beyond the studio. That requires a technique called Elastic Bunch Graph Matching (EBGM), which 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攝像頭前的時候，所有這些標(biāo)準(zhǔn)都好辦，但是在攝影棚外就不那么有用了。這要求一種名為彈性束圖匹配（EBGM）的技術(shù)，該技術(shù)力求通過2D圖像創(chuàng)建一個3D模型。因此這個模型就能用于匹配任何相關(guān)圖片，或其中的部分。
EBGM considers the head as a union of two ellipsoids: one whose main axis is vertical, and runs from forehead to chin; the other whose main axis is horizontal, and runs from tip of the nose to the back of the cranium. This basic scheme is overlaid with “fiducial” points which act as anchors for the modelling. These can be as few as half a dozen (the pupils of the eyes, the corners of the mouth, and so on), or as many, in one system, as 40,000.
EBGM將頭部視為兩個橢圓的結(jié)合體。一個的主軸是垂直的，從前額到下巴；另一個的主軸是水平的，從鼻尖到頭蓋骨后側(cè)。基本方案是通過確定基點位置，定位模型尺寸。基點少則6個（瞳孔，嘴角，等等），多則可能在一個系統(tǒng)中達(dá)到40000個。
EBGM allows the construction of a three-dimensional representation of a face from poorly lit images taken at odd angles, such as a closed-circuit television camera might provide. Once it recognises enough fiducial points it can work out what aspect of a face it is viewing. It then extrapolates the expected positions of other fiducial points. As more data come in from the camera, the model's shape is updated. Given enough horsepower, says a British official, such a system can build a model from as few as 80 pixels located between a subject's eyes—and only two images are needed for a 3D reconstruction.
EBGM可以將小角度拍攝的暗光照片，比如閉路電視所提供的，塑造為三維模型。一旦它捕捉到了足夠的基點，系統(tǒng)就能計算出它所觀測的是面部的那個位置。然后系統(tǒng)推斷出其他基點的預(yù)期位置。隨著攝像頭提供的數(shù)據(jù)增多，模型的形狀不斷更新。如果有足夠動力，比如英國官方要求，只需要兩張照片，像素少到在人物的眼睛中只有80個像素，這個系統(tǒng)就能偶建立出3D復(fù)原模型。
Governments are not the only ones interested. Earlier this year, Facebook's DeepFace system was asked whether thousands of pairs of photos were of the same person. It answered correctly 97.25% of the time, a shade behind humans at 97.53%. Although DeepFace is only a research project, and is aided by the fact that many Facebook photos are tagged with the names of people in the images, which lets the system learn those faces in different poses and lighting conditions, it is still an impressive feat.
并不只有政府對此感興趣。今年早些時候，有人拿臉譜的“深臉”系統(tǒng)測試了成千上萬張照片，看他們是否是同一個人。其正確率為97.25%，在人背后后有陰影的情況下識別率為97.53%。盡管深臉只是研究項目，并且臉譜上的許多照片都是貼著人的姓名這個情況給出了一定幫助，使得系統(tǒng)能夠辨別出不同姿勢、不同采光下的人臉，但是這個成果仍舊令人矚目。
As DeepFace shows, access to an accurate gallery of images is crucial. Passport photos, or those on national identity cards, can act as such galleries, as they can be rendered by EBGM into usable 3D models. Add in the increasing ubiquity of closed-circuit television, and the idea that anyone will be able hide for long in Nepal, or anywhere else, looks quaint.
正如深臉?biāo)@示的，想精確識別大批量圖案依然困難重重。護照照片，或者那些用在國民身份證上的，可以作為這種相片管理系統(tǒng)，因為他們可以可以由EBGM轉(zhuǎn)述為實用3D模型。再考慮到閉路電視的普及，那么任何一個人，想要在尼泊爾或者其他任何地方藏起來的這種想法都會變得不切實際。
