[talk] Might be OT to list

Edward Capriolo edlinuxguru at gmail.com
Mon Jun 20 11:29:26 EDT 2016


For text processing there are multiple algorithms to extract meaning from
text. One is LDA:
http://chrisstrelioff.ws/sandbox/2014/11/13/getting_started_with_latent_dirichlet_allocation_in_python.html

Image processing is more involved. I would guess google uses ALT text and
other content on the page.

Fun reading:

https://www.theguardian.com/technology/2016/apr/08/does-google-unprofessional-hair-results-prove-algorithms-racist-

On Mon, Jun 20, 2016 at 11:15 AM, Sujit K M <kmsujit at gmail.com> wrote:

> Hi All,
>
> I found something interesting with youtube, I believe it is more to do
> with machine learning and image processing etc.
>
> If you search for grey washing machine or red washing machine you get
> an grey or red washing machine.
> If you search for grey balloon or red balloon you get an grey or red
> balloon.
>
> Could any one of you probably direct me to an google sponsored or an
> Opensource library which uses machine learning
> and image processing to achieve this.
>
> Regards,
> Sujit K M
>
> _______________________________________________
> talk mailing list
> talk at lists.nycbug.org
> http://lists.nycbug.org/mailman/listinfo/talk
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.nycbug.org/pipermail/talk/attachments/20160620/2642f9d1/attachment.html>


More information about the talk mailing list