Re: Microsoft's object recognition technology and Cloud questions for NVDA


Antony Stone
 

The description feature for Windows 10 sounds interesting. Please can you
post a link where we can read more about it?

Microsoft is not well known for releasing its software under open source
licences (it has done so to some extent in recent years, but it's the
exception rather than the rule), therefore I think it unlikely, but any
announcement from Microsoft about the feature itself would be the definitive
source of information.

I don't understand your question "Can not we do this with the same DLL as we
do in the same OCR?" - please could you rephrase it?

Similarly, what does "can we deal with a cloud system?" mean? Any computer
which is online can access cloud computing resources. What were you asking
about specifically?


Antony.

On Sunday 21 January 2018 at 17:30:50, Shasa wrote:

Microsoft has introduced a description feature that allows Windows 10 to
recognize objects, images, and other non-resolvable content on its
screen reader.
Is this open source by Microsoft? Can not we do this with the same DLL
as we do in the same OCR?

Finally, Python has great capabilities in the visual part. Legends
emerged especially with the development of artificial intelligence. Can
we deal with a cloud system?
--
If you were ploughing a field, which would you rather use - two strong oxen or
1024 chickens?

- Seymour Cray, pioneer of supercomputing

Please reply to the list;
please *don't* CC me.

Join nvda@nvda.groups.io to automatically receive all group messages.