Recently I had a project come across my desk that could use a bit of image classification and labeling to identify and tag products in photos. AWS Rekognition was the first thing that came to mind. Well actually YOLO was the first, but I didn’t think it was quite robust enough for the project.

It turns out currently it has the ability to label approximately 3083 different types of objects(Oddly enough this includes Batman and Super Mario). Additionally you can add your own custom labels to it which would be interesting. (The Main Youtube Video on Training Custom Labels with AWS Rekognition is a bit rough though… perhaps I should make a video on it).

Another idea I had was to build a very niche consulting company that specializes in OCR and Image Labeling. Could be an interesting endeavor. Let me know if you have a project that could use AWS Rekognition. Always curious to hear what other hacker types are working on.

~Cheers

PS: If you are interested in engaging my services as a Web Application Architect check out my Group Coaching Program or 1 on 1 Consulting at schematical.com and check out my FREE eBook 20 Things You Can DoTo Save Money On Your Amazon Web Services Bill Today