3
$\begingroup$

I was checking services like Microsoft Azure's Cognitive Services Computer Vision API and Google's Vision API and they are amazing. I was wondering if these services, or any other cloud service for that matter, can recognize an image's content and classify it on a set of fixed categories defined by me, not by the Cognitive Service provider.

For example, I have different products and I will take several pictures of each product. I want to then use the cloud service and upload all the pictures of each product, so that I can then take a picture of one product and the Computer Vision algorithm will tell me which product I am seeing.

Is it possible? Is there a third party solution for this problem? If so, how many pictures do I need to train each product's recognition?

I hope I was clear. Thanks in advance for any light on the topic!

$\endgroup$
3
$\begingroup$

Actually I'm trying the same thing with the Azure Computer Vision API. Although the API is very good in identifying objects, it has problems identifying specific consumer products (in my experience though). For example it can't really distinguish between two pair of shoes, or two pair of watches.

People recommended me using the: Custom Vision Service combined with Custom Decision Service. I haven't really looked in to them both. But maybe it's useful for you.

$\endgroup$
1
$\begingroup$

You can check the cloudcv : https://cloudcv.org/trainaclass/ you can use the web service or call throw matlab or python api

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.