Microsoft recently launched an app called “How Do I Look” that determines people’s age and gender using their photos. The feature is available for use on the how-old.net website, as revealed by the software company at its Build developers’ conference in San Francisco yesterday.
How the app works
It is suggested that the website is aimed at displaying the abilities of the company’s face-detection API tools and its Azure computing program. Being a component of Microsoft’s Project Oxford, the face detection API is capable of analyzing images, identifying faces and performing more challenging functions, for instance, detecting the same person in other pictures. Moreover, it is well-equipped to operate with other third-party apps for a number of purposes such as photo editing, organizing a library of images, etc. The new tool determines all of this using a database of faces with their ages and genders.
According to a Microsoft blog post, the website was designed by its creators in a single day. Its development included the application of Machine Learning APIs, real-time streaming analytics and real-time BI. Further, the blog noted that the website works by first extracting information like age and gender from the images uploaded by people. Then this information is analyzed in real time using the company’s Azure streaming services, and the result is finally displayed on the website using real time dashboards.
David Einhorn Buys Three New Stocks: These Are The Names And Theses (Q3 Letter)
David Einhorn's Greenlight Capital funds returned 5.9% in the third quarter of 2020, compared to a gain of 8.9% for the S&P 500 in the same period. This year has been particularly challenging for value investors. Growth stocks have surged as value has struggled. For Greenlight, one of Wall Street's most established value-focused investment funds, Read More
Microsoft app already popular
After just a few hours of its release, the website became hugely popular on the internet and was used by more than 35,000 people around the globe. Many were baffled as the predictions miscalculated their ages, sometimes overestimating by multiple decades, according to CNN. Moreover, research found that more than 50% of the images analyzed by people were their own, contrary to the beliefs of some who initially thought people would prefer to use random images for analysis.
Designed to be a fun experience and to attract people around the world, the website turned out to be a substantial example that displays the ability of Microsoft’s Azure services. Similar to other tech companies, Microsoft is making efforts to develop machine learning technology that could be used to organize the huge database of Internet pictures in a better way. Along with face detection, the company is also working on speech recognition and image processing systems.