Openverse Reviews

Amazon Rekognition Reviews

Openverse mentions (4)

• Museums with CC0 Collections

  Also see https://wordpress.org/openverse/ it allows you to filter to only public domain images. - Source: Hacker News / over 1 year ago

• Google Broke Image Search for Creative Commons and Hardly Anyone Noticed

  Thanks for the HN treatment. As a followup piece, a Google response of this being "a bug". Followup story, my return rate for CC licensed images of "dog" went from 3 to 13. More than that, license info is not displayed (only linked), is frequently wrong, and photo credits often given to the site, not the creator of the image. https://cogdogblog.com/2022/10/google-cc-image-search-better-sad/ Try Openverse for much... - Source: Hacker News / over 1 year ago

• Google Broke Image Search for Creative Commons and Hardly Anyone Noticed

  Last time I've checked, Creative Commons had their own search for things under their licenses. But now apparently that project got transferred to WordPress and is now named Openverse: https://wordpress.org/openverse/?referrer=creativecommons.org Anyways, I'd argue that's the most comprehensive database of CC-licensed works. - Source: Hacker News / over 1 year ago

• Best Practices for Attribution

  > In addition, a searchable database of Creative Commons works would be a welcome addition to the Internet. Openverse is a CC search engine with 600 million items: https://wordpress.org/openverse/ And of course, Google Images supports CC search for images. - Source: Hacker News / almost 2 years ago

Amazon Rekognition mentions (33)

• Afraid of outgrowing AWS Rekognition? Try YOLO in Lambda.

  AWS Rekognition is a great choice for many types of real-world projects or just for testing an idea on your images. The issue eventually comes with its cost, unfortunately, which we will see later in a specific example. Don’t get me wrong, Rekognition is a great service and I love to use it for its simplicity and reliable performance on quite a few projects. - Source: dev.to / 3 months ago

• Amazon Rekognition Custom Labels for Bears

  I don’t really want to spend so much time manually adjusting labels. For most machine learning, the next step would be to fine tune your model. You can essentially fine tune Amazon Rekognition by using Custom Labels. You can do this to make it better at detecting specific objects (like bears) or train it to detect new objects like your product or logo. It really depends on your application needs. - Source: dev.to / 11 months ago

• “During a gold rush, sell shovels.” What are the shovels in the AI rush?

  For instance, are you a company with lots of security cameras? Hire me to write a program that pipes your data into AWS rekognition and then shows you a dashboard of what happened on your cams today. Got a ton of products with no meta-description? Hire me to write a program that pipes your data into OpenAI, and then saves the generated description to your custom CMS. Source: 12 months ago

• Serverless Facial Recognition Voting Application Using AWS Services

  Amazon Rekognition: Used to index, detect faces in the picture, and compare faces when users try voting, it was the heart of the facial voting feature. - Source: dev.to / about 1 year ago

• Amazon Prime Video playback features

  Sure. But if you think generating thumbnails and detecting intros/credits takes a long time, wait until your computer is running machine learning/computer vision over your entire library. They also have to build and train that model which is no trivial task. And I know what you're thinking, why don't they just use Amazon's Rekognition service that does celebrity identification? Well, it's $0.10 per minute of... Source: over 1 year ago