Overall Satisfaction with Amazon Rekognition
Amazon Rekognition is a very easy solution to add image and video analysis to our applications using simple API calls. It is very easy to use and adding image tagging, object recognition, and various other image analysis has become too easy for us to add to any software or web app. Also, video tagging of it is very good and can be used for professional development.
- Easy to use.
- Costs get effected due to its subscription pricing.
Very much suitable for many applications where the image processing features are secondary and independent of any domain. This makes it a general solution and the recognition features are returned in a JSON object in response to the API called made which is a very simple process.
Had to use it for Python and its documentation was so great that I didn't have to go to any other references for implementing it.
- Microsoft Cognitive Toolkit (CNTK)
It's easy to implement and its documentation is great compared to CNTK.
It is very well suited for image processing and recognition based applications and can be easily used using API calls without actually. writing any code for image processing. It can be used with any professional software development as it is built with so much precision. I would not suggest it for a sole feature-based application like image tagging only because for that you can create your own algorithm specific to a domain you want.