It designed to site to show off the capabilities of its cloud server software.
微軟設(shè)計(jì)這個(gè)網(wǎng)站是為了體現(xiàn)其云服務(wù)器軟件的性能.
It revealed the site today at its annual Build developers conference in San Francisco.
在當(dāng)?shù)貢r(shí)間4月30日于舊金山舉辦的年度Build開(kāi)發(fā)者大會(huì)上,微軟公布了這個(gè)網(wǎng)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.
微軟表示："我們想開(kāi)發(fā)一款足夠智能的產(chǎn)品,抓住全世界人們的目光,因此我們?cè)贏zure機(jī)器學(xué)習(xí)庫(kù)（Azure Machine Learning Gallery）中查找可利用的編程接口（APIs）."
The system works by analysing 27 points on the face.
這個(gè)系統(tǒng)將在人的面部選取27個(gè)點(diǎn)并進(jìn)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.
系統(tǒng)將這27個(gè)點(diǎn)稱為"臉部地標(biāo)",選取的是一系列非常能夠體現(xiàn)面部特征的點(diǎn)；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.
"該應(yīng)用是通過(guò)統(tǒng)計(jì)學(xué)算法來(lái)對(duì)這些特征進(jìn)行測(cè)算,有時(shí)并非百分之百準(zhǔn)確."
'However, they are still helpful when you want to classify faces by these attributes.
"然而,當(dāng)我們想要通過(guò)這些特征來(lái)鑒別人的面部時(shí),這個(gè)應(yīng)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.
"'臉部地標(biāo)'是臉部一系列非常能夠顯示面部特征的點(diǎn)；尤其是像瞳孔,眼角和鼻子.
Face landmarks are optional attributes that can be analyzed during face detection.
"臉部地標(biāo)"是在臉部隨機(jī)選取的特征點(diǎn),系統(tǒng)會(huì)對(duì)人臉部進(jìn)行識(shí)別,繼而對(duì)這些特征點(diǎn)進(jìn)行分析.
By default, there are 27 predefined landmark points.
默認(rèn)情況下,系統(tǒng)將預(yù)先確定27個(gè)這樣的"臉部地標(biāo)".
