New Microsoft app can tell how old you are from photos

微软"测颜龄"软件红遍网络

New Microsoft app can tell how old you are from photos

It's no secret celebrities spend thousands upon thousands of dollars on maintaining their looks.

世人皆知,明星们为了使自己容颜永驻可谓是不惜一切代价.

From bloody 'vampire facials' to placenta serums and of course plastic surgery - the fountain of youth runs deep.

从敷人血面膜驻颜到胎盘面部护理,明星们为了看起来更年轻真是使出了浑身解数.

But anapp is now trying to cut through all the cosmetics to determine exactly how old a person looks based on a picture.

但现在有一款应用,能够识破你所有"伪装",仅从照片判断你的年龄.

The website, called How old do I look, it allows people to analyse any image found on Bing, Microsoft's search engine, or upload their own.

这个通过分析图片来鉴定年龄的网站叫How old do I look,人们可以上传从微软搜索引擎必应（Bing）上下载的图片,或上传自己的图片,系统将对图片进行分析.

It even allows users to search for celebrities - and see what Microsoft thinks their real ages are.

用户甚至可以在该网站上搜索名人的照片,应用将会测算出该名人的"真实年龄".

'This may be hard to believe but it took a couple of developers just a day to put this whole solution together, starting with the pipeline from the web page to the Machine Learning APIs to the real time streaming analytics and real time B,' said Microsoft.

"这个应用是两个研发人员的劳动成果,他们完成了从网页到机器学习编程接口（Machine Learning APIs）的信息传输,继而完成后者到实时流量分析,再到实时扫描的信息传输,整个过程仅用了一天时间,这非常不可思议."微软有关人员表示.

It designed to site to show off the capabilities of its cloud server software.

微软设计这个网站是为了体现其云服务器软件的性能.

It revealed the site today at its annual Build developers conference in San Francisco.

在当地时间4月30日于旧金山举办的年度Build开发者大会上,微软公布了这个网站.

'We wanted to create an experience that was intelligent and fun could capture the attention of people globally, so we looked at the APIs available in the Azure Machine Learning Gallery,' it said.

微软表示："我们想开发一款足够智能的产品,抓住全世界人们的目光,因此我们在Azure机器学习库（Azure Machine Learning Gallery）中查找可利用的编程接口（APIs）."

The system works by analysing 27 points on the face.

这个系统将在人的面部选取27个点并进行分析.

Called face landmarks, they are a series of specifically detailed points on a face; typically points of face components like the pupils, canthus or nose.

系统将这27个点称为"脸部地标",选取的是一系列非常能够体现面部特征的点；尤其是像瞳孔,眼角和鼻子.

'These attributes are predicted by using statistical algorithms and may not always be 100% precise.

"该应用是通过统计学算法来对这些特征进行测算,有时并非百分之百准确."

'However, they are still helpful when you want to classify faces by these attributes.

"然而,当我们想要通过这些特征来鉴别人的面部时,这个应用仍然有其用武之地."

'Face landmarks are a series of specifically detailed points on a face; typically points of face components like the pupils, canthus or nose.

"'脸部地标'是脸部一系列非常能够显示面部特征的点；尤其是像瞳孔,眼角和鼻子.

Face landmarks are optional attributes that can be analyzed during face detection.

"脸部地标"是在脸部随机选取的特征点,系统会对人脸部进行识别,继而对这些特征点进行分析.

By default, there are 27 predefined landmark points.

默认情况下,系统将预先确定27个这样的"脸部地标".