Since researchers started performing on AI, one among the first goals has always been a complicated image captioning system. Many companies are investing their precious resources in AI to develop better and better products. Now, Microsoft has come up with a replacement AI system which will caption and describe images more accurately than humans can.
The Tech giant recently announced this breakthrough via a politician blog post. Although image captioning is one among the toughest tasks for an AI system to master, Microsoft says that their new “Enhanced Image Captioning” AI has image captioning abilities nearly as good as humans. And this breakthrough in AI technology will help the corporate boost its products and services within the market.
Now, automatic image captioning won’t sound like a crucial feat, but believe me, it is. This nifty technology helps users access the content in a picture , whether it’s in your gallery or somewhere during a 5-page document. as an example , once you look for “dog” in your image gallery, the designated app uses its image recognition capabilities to mapped out every picture that features a dog in it then narrow it right down to your search. this is often one among the various tasks which needs a system to possess great image recognition capabilities.
Microsoft’s new model can generate way better captions for images than its predecessors. And these captions are, indeed, almost like what a person’s would write to explain the pictures .
as you’ll see, the new “Enhanced Image Captioning” AI is far more accurate in its description of a picture than before. Moreover, this new model can even recognize the context of a picture .
In this image above, the previous system gave a vague description without telling what the players do . However, the new model knows that the players are celebrating and are literally football players, not baseball players!
Now, this image captioning capability is beneficial for users, but the people for whom this technology is of utmost importance are those that are blind or have low vision. These people need to believe voice dictations when navigating through computer systems. So, image captioning helps them flick through social media or messages more easily.
“The use of image captioning to get a photograph description, referred to as alt text, during a website or document is particularly important for people that are blind or have low vision,” said Saqib Shaikh, a programmer Manager at Microsoft’s AI division in Redmond.
the Windows maker is now integrating this new image captioning AI system into its talking-camera app, Seeing AI, which is formed especially for the visually-impaired. This app uses the image captioning capabilities of the AI to explain pictures in users’ mobile devices, and even in social media profiles.
Apart from integration within the Seeing AI app, Microsoft also made the new AI-system available for Azure AI clients. It now exists as a neighborhood of the Azure Cognitive Services Computer Vision and developers can use its capabilities in their own apps and services, if they want to.
Moreover, the AI image captioning tech also will make its thanks to Microsoft Office apps, like Microsoft Word, PowerPoint, and Outlook, later this year.