Image Analysis is defined in wikipedia as “…the extraction of meaningful information from images; mainly from digital images by means of digital image processing techniques”
We used the Cognitive API Integrator to compare the response of these 3 major cognitive API providers and came up with some interesting results.
- All three service providers do a good job at detecting the main elements on the image.
- Azure is the only provider that gives a nice caption to give more “context” to the image.
- Azure and AWS both give some irrelevant tags. Google gives lesser tags but more relevant ones
- Overall Azure and AWS both focus on detecting the various objects in the image rather than the “context” of the image. Google seems to focus more on analyzing the context of the image rather than detecting various objects in it
Lets take a look at a few examples
Example 1:- A Birthday party
- While AWS gives a lot of tags it fails to recognize the overall theme i.e a birthday party
- Azure pretty much gets it spot on with its caption
- Google is able to communicate the context via its descriptive tags
Example 2:- A group of children studying
- Google has the most relevant tags which are able to communicate what is happening in the image
- Azure has an almost relevant caption but has some irrelevant tags (mother, birthday etc)
- AWS has some relevant tags but is still unable to communicate the context.
About the Cognitive API Integrator
The Cognitive API Integrator aggregates cognitive services across major providers (currently Microsoft Azure, Amazon Web Services & Google Cloud) . Use it to compare responses for various Cognitive APIs before making your selection of which provider you will integrate with.
Note:- The Cognitive API Integrator does not aim to promote or downplay any Cognitive API Provider. Cognitive Analysis is a machine learning exercise where results are bound to improve with more data and usage. Conclusions drawn here can be subjective and users are encouraged to use the tool to form their own conclusions.