????Facebook近日發(fā)布了一款名叫Moments的產(chǎn)品。它使用Facebook的人臉識別技術(shù)，為你的朋友掃描你的照片，然后讓人們與一個(gè)特定群組（比如照片中的人）

????創(chuàng)建私人相冊。這樣一來，在大型活動(dòng)結(jié)束后，人們就免去了用電子郵件一張張地互相發(fā)照片的麻煩，或是所有拿到手的都是同一張“大合影”的尷尬。它并非是像治愈癌癥那樣重大的發(fā)明，但在這項(xiàng)新功能的背后，卻是一項(xiàng)Facebook已經(jīng)苦心鉆研了多年的技術(shù)。

????Moments功能的核心元素之一，是在不同的照片中識別人臉?biāo)玫乃惴ǎ@樣Moments才能知道誰出席了這次活動(dòng)。要做到這一點(diǎn)，就需要高超的計(jì)算機(jī)視覺技術(shù)。目前包括谷歌、微軟和百度在內(nèi)的多家科技公司都在研究該技術(shù)，因?yàn)樗膽?yīng)用前景極其廣泛，既可用于自動(dòng)駕駛汽車，也可用于像微軟的“顏齡神器”這種除了賣萌耍寶之外，不知道干什么用的產(chǎn)品。

????在Moments發(fā)布的過程中，F(xiàn)acebook也分享了它在計(jì)算機(jī)視覺研究方面取得的進(jìn)展。目前Facebook的人臉識別技術(shù)達(dá)到了98%的準(zhǔn)確性，而且識別所需的時(shí)間很短。該公司稱，只需要不到5秒鐘的時(shí)間，它的人臉識別技術(shù)就能在800萬張照片中迅速地找到你的臉。另外，哪怕你在照片中出現(xiàn)的不是正臉（或者甚至你根本沒在照片里露面），計(jì)算機(jī)也能精準(zhǔn)地識別出來。這要?dú)w功于Facebook開發(fā)的一種機(jī)器學(xué)習(xí)算法，它能參考照片的其它元素，然后與照片的數(shù)據(jù)進(jìn)行關(guān)聯(lián)。

????Facebook today launched its Moments product, which uses Facebook’s image recognition abilities to scan your photos for your friends and then lets people create private photo albums with a particular group, such as the people in the photo. The idea is to make it easier to share photos from a big event among attendees without the cumbersome process of emailing snapshots to everyone or the awkward end-of-event huddle while six people take the exact same group shot. It’s not a cure for cancer, but behind the scenes of this new feature is an impressive technology that Facebook has been working on for years.

????A key element of the Moments feature is the ability for Facebook’s algorithms to recognize people’s faces across different photos, so that Moments knows who was at the event. This requires computer vision expertise that companies such as Google, Microsoft, Baidu, and others are currently researching for everything from self-driving cars to silly web products such as Microsoft’s How Old Do I Look?

????In launching the Moments product Facebook is sharing data about its own successes in computer vision research. Namely, that Facebook can recognize faces with a 98% accuracy, and it can do so quickly—the company says it can identify you in one picture out of 800 million in less than 5 seconds. Finally, it can do all of this even if it doesn’t have the full frontal shot of your face (or even if your face isn’t in the photo at all), thanks to a machine learning algorithm that can look at other elements in the picture and associated with the photo’s data.

????Moments的背后

????《財(cái)富》采訪了Facebook的人工智能研究主管嚴(yán)恩?樂昆，以了解他的團(tuán)隊(duì)是如何讓計(jì)算機(jī)學(xué)會(huì)人臉識別的，以及Facebook的人工智能研究下一步將向什么方向發(fā)展。首先我們需要了解的是，計(jì)算機(jī)視覺和人類看東西的方式是不一樣的，不過教軟件學(xué)習(xí)識別物體的過程與人類的視覺模式倒是有些相似。

????比如，F(xiàn)acebook的面部識別技術(shù)其實(shí)無法辯識“你”這個(gè)人，它只能識別出一張照片中的“你”和另一張照片中的“你”是不是同一個(gè)人。真正意義上的鑒定身份，則完全是另一個(gè)階段的事。

????由于Facebook是一個(gè)人際社交網(wǎng)絡(luò)，它的計(jì)算機(jī)視覺技術(shù)一直專注于識別人臉，而不是識別貓貓狗狗、汽車或者其他非人物體。Facebook使用了一個(gè)全球名人和政客的臉部照片數(shù)據(jù)庫，這個(gè)名為“戶外臉部檢測”的數(shù)據(jù)庫擁有超過1.3萬張人物照片，他們的發(fā)型和穿著均不相同，有的戴著眼鏡或其他配飾。除了Facebook之外，還有其他公司也在使用這個(gè)數(shù)據(jù)庫，一些使用戶外臉部檢測數(shù)據(jù)庫的大學(xué)甚至將這套系統(tǒng)的識別準(zhǔn)確率提高至98%以上。

????那么，從讓電腦看安吉莉娜?朱莉的照片開始，F(xiàn)acebook是怎樣做到能夠從全網(wǎng)的各個(gè)相冊中找到你妹妹的照片的呢？這個(gè)問題就得讓嚴(yán)恩?樂昆來回答了。大約20年前他還在貝爾工作室（現(xiàn)在已經(jīng)變成AT&T的圖像處理研究部門）工作的時(shí)候，他偶然想到了一種教電腦“看”東西的辦法，但這項(xiàng)技術(shù)直到3年前才開始被學(xué)術(shù)界以外使用。

????Inside Moments

????Fortune spoke with Yann LeCun, Facebook’s director of artificial intelligence research, to understand how his team helped a computer understand who you are, and where Facebook is heading next with its AI research. Perhaps the first thing to understand is that when LeCun discusses computer vision, it’s not the same as how a person sees, although the process of teaching software how to recognize an object has some similarities.

????For example, Facebook’s facial recognition, which is the basis of the current efforts, can’t identify you. It only can recognize if a person in one photo is the same as a person in another photo. Identification is a completely separate step.

????Because Facebook is about connecting people, its computer vision efforts have focused on recognizing faces as opposed to cats, cars, or other non-human subjects. To do this, it uses a database of celebrity and politicians photos calledLabeled Faces in the Wild. This collection of images has 13,000 photos of people with different hairdos, different outfits, sometimes wearing glasses and more. Facebook used this collection to train its machine learning algorithms. Other companies have used this data set as well, and some universities have even trained systems with a higher than 98% accuracy rate using Labeled Faces.

????So how did Facebook get from giving a machine a picture of Angelina Jolie to somehow using that photo to help identify your sister across different photo albums on Facebook? LeCun is the man to ask. About 20 years ago when he was working at Bell Labs (now AT&T’s Image Processing Research Department), he happened upon a way of thinking about teaching computers to see that wasn’t really used outside of academia until about three years ago.