[Pywikipedia-l] Using computer vision to categorize images at Commons

List overview All Threads
Download

newer

older

[Pywikipedia-l] Making...

[Pywikipedia-l] SourceForge...

Maarten Dammers

20 Feb 2012 20 Feb '12

10:08 p.m.

Hi everyone, Some time ago I played around with computer vision to get images categorized on Commons. I documented this at https://commons.wikimedia.org/wiki/User:Multichill/Using_OpenCV_to_categori… . I don't think I'm going to spend time on it soon, but the results were quite promising, so maybe someone else feels like working on this? Would probably be a pretty nice student project or just fun to do. Maarten

Show replies by date

Dr. Trigon

20 Feb 20 Feb

10:19 p.m.

New subject: [Pywikipedia-l] Using computer vision to categorize images at Commons

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 This sound intressting indeed. Despite the fact that I do not have a real clue on how to use OpenCV, I played with it myself too (some time ago) - I will keep it in mind for sure!!! I am also thinking about some data extraction from image files for DrTrigonBot subster but this is very premature too. But to at the moment I do not have time to spend on it - I'm really sorry... Greetings DrTrigon On 20.02.2012 22:08, Maarten Dammers wrote:

...

. I don't think I'm going to spend time on it soon, but the results were

...

quite promising, so maybe someone else feels like working on this? Would probably be a pretty nice student project or just fun to do. Maarten _______________________________________________ Pywikipedia-l mailing list Pywikipedia-l(a)lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/pywikipedia-l

...PGP SIGNATURE...

-----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAk9CuPUACgkQAXWvBxzBrDBi8QCeJcPMBeNI1BuLTpnqG+Bu9AEG lZMAn0ekD3MBWc7VfSxa/a7b3blLgxoa =ia7S -----END PGP SIGNATURE-----

emijrp

10:47 p.m.

New subject: [Pywikipedia-l] [Wikitech-l] Using computer vision to categorize images at Commons

Hi Maarten; I think that this is a perfect example of open question in wiki research. WikiPapers has a page for that stuff.[1] Can you add some bits there about this? I dind't know about OpenCV, I will check it for sure, and I will try to something (I'm a bot developer). Regards, emijrp [1] http://wikipapers.referata.com/wiki/List_of_open_questions 2012/2/20 Maarten Dammers <maarten(a)mdammers.nl>

...

Hi everyone, Some time ago I played around with computer vision to get images categorized on Commons. I documented this at https://commons.wikimedia.org/**wiki/User:Multichill/Using_** OpenCV_to_categorize_files<https://commons.wikimedia.org/wiki/User:Multi…es>. I don't think I'm going to spend time on it soon, but the results were quite promising, so maybe someone else feels like working on this? Would probably be a pretty nice student project or just fun to do. Maarten ______________________________**_________________ Wikitech-l mailing list Wikitech-l(a)lists.wikimedia.org https://lists.wikimedia.org/**mailman/listinfo/wikitech-l<https://lists.…

emijrp

21 Feb 21 Feb

12:09 a.m.

New subject: [Pywikipedia-l] [Wikitech-l] Using computer vision to categorize images at Commons

I have found a tutorial for Python coders http://creatingwithcode.com/howto/face-detection-in-static-images-with-pyth… some tests, it works fine (including René Descartes face : )). This is going to be very helpful to improve Images for biographies accuracy http://toolserver.org/~emijrp/imagesforbio/ 2012/2/20 emijrp <emijrp(a)gmail.com>

...

Dr. Trigon

2:01 p.m.

New subject: [Pywikipedia-l] [Wikitech-l] Using computer vision to categorize images at Commons

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Please correct me if I am wrong - this script does "face searching" but not "face recognition". So it gives you the coordinates (a rect) at what points in the image a face is. But it is not able to compare this face with others and give it a rate like 75% agreement, or something like this... Anyway it is a step forward. Btw.: If it is of intresst; I tried to recongize a rubik cube from webcam (live; moving images) and aquire the face colors while rotating the cube by hands... this worked not very well but under some circumstances... ;) The example I used was [1]/[2]. The move impressed me... ;)) [1] http://www.youtube.com/watch?v=VaW1dmqRE0o [2] http://www.cs.ubc.ca/~andrejk/525project/ On 21.02.2012 00:09, emijrp wrote:

...

I have found a tutorial for Python coders http://creatingwithcode.com/howto/face-detection-in-static-images-with-pyth…

After some tests, it works fine (including René Descartes face : )).

...

This is going to be very helpful to improve Images for biographies accuracy http://toolserver.org/~emijrp/imagesforbio/ 2012/2/20 emijrp <emijrp(a)gmail.com <mailto:emijrp@gmail.com>> Hi Maarten; I think that this is a perfect example of open question in wiki research. WikiPapers has a page for that stuff.[1] Can you add some bits there about this? I dind't know about OpenCV, I will check it for sure, and I will try to something (I'm a bot developer). Regards, emijrp [1] http://wikipapers.referata.com/wiki/List_of_open_questions 2012/2/20 Maarten Dammers <maarten(a)mdammers.nl <mailto:maarten@mdammers.nl>> Hi everyone, Some time ago I played around with computer vision to get images categorized on Commons. I documented this at https://commons.wikimedia.org/__wiki/User:Multichill/Using___OpenCV_to_cate…

<https://commons.wikimedia.org/wiki/User:Multichill/Using_OpenCV_to_categorize_files>

...

. I don't think I'm going to spend time on it soon, but the results were quite promising, so maybe someone else feels like working on this? Would probably be a pretty nice student project or just fun to do. Maarten _________________________________________________ Wikitech-l mailing list Wikitech-l(a)lists.wikimedia.org <mailto:Wikitech-l@lists.wikimedia.org> https://lists.wikimedia.org/__mailman/listinfo/wikitech-l <https://lists.wikimedia.org/mailman/listinfo/wikitech-l> _______________________________________________ Pywikipedia-l mailing list Pywikipedia-l(a)lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/pywikipedia-l

...PGP SIGNATURE...

-----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAk9DlacACgkQAXWvBxzBrDD2VACfcdtUxYjf0lMrWHD+N75B6NZU AMkAniwnXzCF/Y0pX18xi6xfB8E7rHZP =XRXX -----END PGP SIGNATURE-----

Antoine Musso

8:09 a.m.

Le 20/02/12 22:08, Maarten Dammers a écrit :

...

Some time ago I played around with computer vision to get images categorized on Commons. I documented this at https://commons.wikimedia.org/wiki/User:Multichill/Using_OpenCV_to_categori… . I don't think I'm going to spend time on it soon, but the results were quite promising, so maybe someone else feels like working on this? Would probably be a pretty nice student project or just fun to do.

Google used a game to add keywords to images. Two people (of of them could be a robot) were presented two pictures. The aim is to enter a keyword that best describe the picture and that the other people will choose too. If both people use the same keyword, you gain points :-) Imagine, you are being shown a picture whose main subject is a monkey, you enter "monkey", the other one "monkey" too. You both earn points. The game host now know that the picture is of a monkey :-D -- Antoine "hashar" Musso

4448

days inactive

4449

days old

pywikibot@lists.wikimedia.org

Manage subscription

5 comments

4 participants

tags (0)

participants (4)

Antoine Musso
Dr. Trigon
emijrp
Maarten Dammers