New Microsoft Azure AI Breakthrough Gives It Ability To Accurately Caption Images
Microsoft researchers have made a breakthrough in its Azure artificial intelligence field that enables it accurately give image captions. Here are the details about this achievement.
According to the company’s press release, this new model will be available on the Azure Cognitive Services Computer Vision. Also, Microsoft says that it will soon be available in Word and Outlook, for Windows and Mac, and PowerPoint for Windows, Mac and web by the end of 2020 via Seeing AI.
There are many ways that this new capability can be employed. For example, users can use it to quickly get the important content of an image. Also, search engines can use it to improve image search results to a higher degree of accuracy.
Another way it can be used is to improve internet experience for the blind and vision impaired. Saqib Shaikh, a software engineering manager at Microsoft revealed that his team is using this new captioning capability in ‘talking camera app’ for visually impaired people. The app can describe photos, including those from social media platforms, using the AI. Shaikh says that this is important as not many people correctly use alt text for images in documents.
– Singapore Releases AI Ethics And Guide, Should Nigeria Start Considering One As Well?
– With Bosch VitaFresh, You No Longer Need To Throw Food And Vegetables Out
– Here Is A Cybersecurity Show That You Can Join For Free
This is a major aspect of AI tech and Microsoft is not alone in pursuing advancements in this field. Google has been improving work in its image recognition field with its onw AI. However, the search giant’s AI ran into trouble when it misidentified women and people of colour.
Microsoft’s AI will likely not run into this kind of trouble. The system is able to understand and describe the salient content or action in an image, Lijuan Wang, a principal research manager in Microsoft’s research lab explained.
“When evaluated on nocaps, the AI system created captions that were more descriptive and accurate than the captions for the same images that were written by people,” Microsoft wrote. This image captioning breakthrough is part of Microsoft’s goal of achieving human parity across its cognitive AI system.
For your daily dose of tech, lifestyle, and trending content, make sure to follow Plat4om on Twitter @Plat4omLive, on Instagram @Plat4om, on LinkedIn at Plat4om, and on Facebook at Plat4om. You can also email us at firstname.lastname@example.org and join our channel on Telegram at Plat4om. Finally, don’t forget to subscribe to our YouTube channel HERE.