Skip to content

Latest commit

 

History

History
24 lines (15 loc) · 1.33 KB

File metadata and controls

24 lines (15 loc) · 1.33 KB

Image Analysis with Azure Computer Vision 4.0 Captioning and Dense Captioning

"Caption" replaces "Describe" in V4.0 as the significantly improved image captioning feature rich with details and sematic understanding.

  • Dense Captions provides more detail by generating one sentence descriptions of up to 10 regions of the image in addition to describing the whole image.
  • Dense Captions also returns bounding box coordinates of the described image regions.
  • There's also a new gender-neutral parameter to allow customers to choose whether to enable probabilistic gender inference for alt-text and Seeing AI applications.
  • Automatically deliver rich captions, accessible alt-text, SEO optimization, and intelligent photo curation to support digital content.

This service is currently in preview, and the API may change in the future.

https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-describe-images-40?tabs=image

Python demo notebook

Python demo notebook

Results

Dense captions from the image

13-Mar-2023 Serge Retkowsky | serge.retkowsky@microsoft.com | https://www.linkedin.com/in/serger/