订阅

多平台阅读

微信订阅

杂志

申请纸刊赠阅

订阅每日电邮

移动应用

商业 - 科技

Facebook如何教电脑“看”人

Stacey Higginbotham 2015年06月25日

Facebook日前发布了一种名为Moments,使用人脸识别技术的功能。该公司称,只需要不到5秒钟的时间,它的人脸识别技术就能在800万张照片中迅速地找到你的脸,目前准确性可达到98%。不过,凭借更出色的电脑视觉和人工智能技术,这家社交巨擘最终希望实现一个更大的目标——让机器理解人。

    Facebook近日发布了一款名叫Moments的产品。它使用Facebook的人脸识别技术,为你的朋友扫描你的照片,然后让人们与一个特定群组(比如照片中的人)

    创建私人相册。这样一来,在大型活动结束后,人们就免去了用电子邮件一张张地互相发照片的麻烦,或是所有拿到手的都是同一张“大合影”的尴尬。它并非是像治愈癌症那样重大的发明,但在这项新功能的背后,却是一项Facebook已经苦心钻研了多年的技术。

    Moments功能的核心元素之一,是在不同的照片中识别人脸所用的算法,这样Moments才能知道谁出席了这次活动。要做到这一点,就需要高超的计算机视觉技术。目前包括谷歌、微软和百度在内的多家科技公司都在研究该技术,因为它的应用前景极其广泛,既可用于自动驾驶汽车,也可用于像微软的“颜龄神器”这种除了卖萌耍宝之外,不知道干什么用的产品。

    在Moments发布的过程中,Facebook也分享了它在计算机视觉研究方面取得的进展。目前Facebook的人脸识别技术达到了98%的准确性,而且识别所需的时间很短。该公司称,只需要不到5秒钟的时间,它的人脸识别技术就能在800万张照片中迅速地找到你的脸。另外,哪怕你在照片中出现的不是正脸(或者甚至你根本没在照片里露面),计算机也能精准地识别出来。这要归功于Facebook开发的一种机器学习算法,它能参考照片的其它元素,然后与照片的数据进行关联。

    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.

    Facebook

    Moments的背后

    《财富》采访了Facebook的人工智能研究主管严恩?乐昆,以了解他的团队是如何让计算机学会人脸识别的,以及Facebook的人工智能研究下一步将向什么方向发展。首先我们需要了解的是,计算机视觉和人类看东西的方式是不一样的,不过教软件学习识别物体的过程与人类的视觉模式倒是有些相似。

    比如,Facebook的面部识别技术其实无法辩识“你”这个人,它只能识别出一张照片中的“你”和另一张照片中的“你”是不是同一个人。真正意义上的鉴定身份,则完全是另一个阶段的事。

    由于Facebook是一个人际社交网络,它的计算机视觉技术一直专注于识别人脸,而不是识别猫猫狗狗、汽车或者其他非人物体。Facebook使用了一个全球名人和政客的脸部照片数据库,这个名为“户外脸部检测”的数据库拥有超过1.3万张人物照片,他们的发型和穿着均不相同,有的戴着眼镜或其他配饰。除了Facebook之外,还有其他公司也在使用这个数据库,一些使用户外脸部检测数据库的大学甚至将这套系统的识别准确率提高至98%以上。

    那么,从让电脑看安吉莉娜?朱莉的照片开始,Facebook是怎样做到能够从全网的各个相册中找到你妹妹的照片的呢?这个问题就得让严恩?乐昆来回答了。大约20年前他还在贝尔工作室(现在已经变成AT&T的图像处理研究部门)工作的时候,他偶然想到了一种教电脑“看”东西的办法,但这项技术直到3年前才开始被学术界以外使用。

    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.

我来点评

相关稿件

  最新文章

最新文章:

500强情报中心

财富专栏