Comments on: Google Lodges Patent For Reading Text In Images And Video http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/ Startup and Technology News Sat, 11 Oct 2008 15:36:35 +0000 http://wordpress.org/?v=2.5.1 By: Google Continues Bringing Together Analog and Digital http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-2492233 Google Continues Bringing Together Analog and Digital Sun, 05 Oct 2008 19:45:40 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-2492233 [...] showcasing it with speeches made by both candidates in this year’s presidential election. Google has even filed a patent for recognizing text within images and video, so I’m sure we’ll be seeing more from Google in the area of digital-to-analog and [...] [...] showcasing it with speeches made by both candidates in this year’s presidential election. Google has even filed a patent for recognizing text within images and video, so I’m sure we’ll be seeing more from Google in the area of digital-to-analog and [...]

]]> By: B&K: spideri i web 2.0, online oglasi vs. tv oglasi i wordpress statistike | SEO & Internet Marketing Blog http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-2410089 B&K: spideri i web 2.0, online oglasi vs. tv oglasi i wordpress statistike | SEO & Internet Marketing Blog Wed, 16 Jul 2008 13:35:31 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-2410089 [...] Po meni, ovo bi mogla biti jedna od vijesti koja bi mogla promijeniti svijet SEO-a i općenito pretraživanja kakvo poznajemo! Kao i kod Flasha i Ajaxa, pretraživači imaju problem sa čitanjem slika i videa koje se bukvalno svodi na pretraživanje njihovih imena, nema mogućnosti da pretraživači pročitaju tekst koji se nalazi unutar slike ili videa. E, pa TechCrunch kaže da Google ima rješenje za taj problem… [...] [...] Po meni, ovo bi mogla biti jedna od vijesti koja bi mogla promijeniti svijet SEO-a i općenito pretraživanja kakvo poznajemo! Kao i kod Flasha i Ajaxa, pretraživači imaju problem sa čitanjem slika i videa koje se bukvalno svodi na pretraživanje njihovih imena, nema mogućnosti da pretraživači pročitaju tekst koji se nalazi unutar slike ili videa. E, pa TechCrunch kaže da Google ima rješenje za taj problem… [...]

]]> By: Computer Vision for Dummies » Google’s text-in-image patent – another one-click fiasco? http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-2043139 Computer Vision for Dummies » Google’s text-in-image patent – another one-click fiasco? Mon, 17 Mar 2008 18:35:13 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-2043139 [...] TechCrunch. Google filed a patent application “Recognizing Text In Images”. It is supposed to improve [...] [...] TechCrunch. Google filed a patent application “Recognizing Text In Images”. It is supposed to improve [...]

]]> By: Stan Chee dot Com Internet Business » New Google Technology to index text in digital photos and videos http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1921351 Stan Chee dot Com Internet Business » New Google Technology to index text in digital photos and videos Tue, 15 Jan 2008 16:30:36 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1921351 [...] Interested to read more? Follow the following links: Information Week Computer World TechCrunch [...] [...] Interested to read more? Follow the following links: Information Week Computer World TechCrunch [...]

]]> By: MrPaul http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1912117 MrPaul Thu, 10 Jan 2008 00:19:10 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1912117 You mean something like has happened recently with ticketmaster? http://www.nytimes.com/2007/12/16/business/16digi.html?ref=business http://herot.typepad.com/cherot/2007/04/ticketmaster_su.html You mean something like has happened recently with ticketmaster?

http://www.nytimes.com/2007/12.....f=business
http://herot.typepad.com/chero.....er_su.html

]]> By: Qube Media. http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1910212 Qube Media. Wed, 09 Jan 2008 11:13:07 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1910212 <strong>Widening the scope of search...</strong> The ability to search for images and video based on their actual content, rather than keywords or other accompanying info, gets closer. Google has lodged a patent for a method of allowing their search robots to read text that appears... Widening the scope of search…

The ability to search for images and video based on their actual content, rather than keywords or other accompanying info, gets closer. Google has lodged a patent for a method of allowing their search robots to read text that appears…

]]> By: Dirk Holland http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1908381 Dirk Holland Tue, 08 Jan 2008 23:27:24 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1908381 We have already developed a product that does this. In addition to finding text it is also able to find brand logos etc. in user generated video. Findit LLC We have already developed a product that does this. In addition to finding text it is also able to find brand logos etc. in user generated video.

Findit LLC

]]> By: seoz87 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1901810 seoz87 Mon, 07 Jan 2008 04:44:57 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1901810 Now this indeed is serious development. Now this indeed is serious development.

]]> By: Thibaut Barrère http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1901660 Thibaut Barrère Mon, 07 Jan 2008 02:56:19 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1901660 I'm wondering if SEO with Flash content will be impacted by that - I suppose so. I’m wondering if SEO with Flash content will be impacted by that - I suppose so.

]]> By: Google brevetta il riconoscimento del testo nelle immagini http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1901421 Google brevetta il riconoscimento del testo nelle immagini Sun, 06 Jan 2008 23:04:45 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1901421 [...] Video: come suggerisce anche TechCrunch, il riconoscimento dei testi potrebbe essere esteso ai video: immaginate YouTube con (alcuni) video [...] [...] Video: come suggerisce anche TechCrunch, il riconoscimento dei testi potrebbe essere esteso ai video: immaginate YouTube con (alcuni) video [...]

]]> By: Silvia http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1901335 Silvia Sun, 06 Jan 2008 20:02:06 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1901335 There's a publication from the year 2000 about how to do text recognition in video by segmenting regions and then using OCR on those regions: http://portal.acm.org/citation.cfm?id=329351. It seems to me that much of what Google is patenting is covered by research publications from that area. Of course, a proper analysis by a patent attorney would be necessary to evaluate the real value of the patent. There’s a publication from the year 2000 about how to do text recognition in video by segmenting regions and then using OCR on those regions: http://portal.acm.org/citation.cfm?id=329351. It seems to me that much of what Google is patenting is covered by research publications from that area. Of course, a proper analysis by a patent attorney would be necessary to evaluate the real value of the patent.

]]> By: links for 2008-01-06 :: robteix.com http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900656 links for 2008-01-06 :: robteix.com Sun, 06 Jan 2008 03:30:31 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900656 [...] Google Lodges Patent For Reading Text In Images And Video (tags: google patents) [...] [...] Google Lodges Patent For Reading Text In Images And Video (tags: google patents) [...]

]]> By: Igor http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900369 Igor Sat, 05 Jan 2008 20:52:05 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900369 Someone already pointed you to EverNote ( http://www.evernote.com/products/evernote/how_to/note_types_tips.php#images ): it can recognize text in images (photos, scans, snapshots, even photos from crappy phone cameras, printed or handwritten text) pretty well. Someone already pointed you to EverNote ( http://www.evernote.com/produc.....php#images ): it can recognize text in images (photos, scans, snapshots, even photos from crappy phone cameras, printed or handwritten text) pretty well.

]]> By: Alex Linhares http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900234 Alex Linhares Sat, 05 Jan 2008 16:36:34 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900234 Vaporware; Hypeware. We're at least some 10 years away from that. Vaporware; Hypeware. We’re at least some 10 years away from that.

]]> By: Bill Slawski http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900217 Bill Slawski Sat, 05 Jan 2008 16:08:38 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900217 Hi Duncan, There are actually three Google patent applications which detail this method, and not just one. Recognizing text in images (20080002893) Enhancing text in images (20080002914) Using extracted image text (20080002916) The character recognition processes for Google Book Search are described in patent applications from Google that came out in 2006. Here's one of them: Presentation of search results based on document structure (20060074907) This is already being done by Google for book search. Hi Duncan,

There are actually three Google patent applications which detail this method, and not just one.

Recognizing text in images (20080002893)
Enhancing text in images (20080002914)
Using extracted image text (20080002916)

The character recognition processes for Google Book Search are described in patent applications from Google that came out in 2006. Here’s one of them:

Presentation of search results based on document structure (20060074907)

This is already being done by Google for book search.

]]> By: halil http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900115 halil Sat, 05 Jan 2008 13:04:49 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900115 valla çok güsel bi şey yapmışsınız ne diyim helal olsun uraştınıza deycene emin olabilirsiniz bütün arkadaşlarıma önericem valla çok güsel bi şey yapmışsınız ne diyim helal olsun uraştınıza deycene emin olabilirsiniz bütün arkadaşlarıma önericem

]]> By: micfo.com http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900028 micfo.com Sat, 05 Jan 2008 10:27:36 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1900028 The search capabilities of the future may be going to index sound too. :) The search capabilities of the future may be going to index sound too. :)

]]> By: Nigel http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899972 Nigel Sat, 05 Jan 2008 08:27:54 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899972 Evernote - the note-taking/web-clipping app has been doing this for ages, it is pretty neat the first time you see it. Evernote - the note-taking/web-clipping app has been doing this for ages, it is pretty neat the first time you see it.

]]> By: Don Jones http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899830 Don Jones Sat, 05 Jan 2008 04:18:52 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899830 This one will be tough for Google to enforce. There is so much technology around text recognition. This one will be tough for Google to enforce. There is so much technology around text recognition.

]]> By: HamishE http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899777 HamishE Sat, 05 Jan 2008 02:55:36 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899777 If the US Patent Office lets this through then they have lost the plot. Last time I checked a "moving image" was nothing more than a sequence of "still images" display in sequence?? Digital Video, TV ... all are simply displaying X Frames per second ... where each Frame is a still image. Even if Google were taking the time-axis into account ... they are simply stacking a series of still images for analysis - blah. The UK Police, Australian Police, and Toll Road operators around the world us OCR on Number Plates daily (still images taken from Video). Oh - and dont our "eyes" do this for us constantly? There is nothing novel or new about this attempt by a corporate giant (who cares if they "do-no-evil") to patent the bleeding obvious! HamishE If the US Patent Office lets this through then they have lost the plot.

Last time I checked a “moving image” was nothing more than a sequence of “still images” display in sequence?? Digital Video, TV … all are simply displaying X Frames per second … where each Frame is a still image. Even if Google were taking the time-axis into account … they are simply stacking a series of still images for analysis - blah.

The UK Police, Australian Police, and Toll Road operators around the world us OCR on Number Plates daily (still images taken from Video).

Oh - and dont our “eyes” do this for us constantly?

There is nothing novel or new about this attempt by a corporate giant (who cares if they “do-no-evil”) to patent the bleeding obvious!

HamishE

]]> By: Kevin Burton http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899728 Kevin Burton Sat, 05 Jan 2008 01:54:45 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899728 Paul Ford's Aug 2009 prediction is looking interesting: http://feedblog.org/2008/01/04/google-indexes-my-groceries-crawling-the-real-world/ I guess I'm going to have to implement this in Spinn3r now :-P Paul Ford’s Aug 2009 prediction is looking interesting:

http://feedblog.org/2008/01/04.....eal-world/

I guess I’m going to have to implement this in Spinn3r now :-P

]]> By: ONLINE SERVICES/INTERACTIVE MEDIA « Daily Marauder http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899625 ONLINE SERVICES/INTERACTIVE MEDIA « Daily Marauder Sat, 05 Jan 2008 00:27:44 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899625 [...] the image or video itself, a big step forward in indexing that has not previously been available. (http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video [...] [...] the image or video itself, a big step forward in indexing that has not previously been available. (http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video [...]

]]> By: Craig Cockburn http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899566 Craig Cockburn Fri, 04 Jan 2008 23:23:29 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899566 I wrote a program to do OCR in the mid 80s and even then it was a far from new idea, with the post office having such systems to scan postcodes before then. So, I'm not sure what's new here? I wrote a program to do OCR in the mid 80s and even then it was a far from new idea, with the post office having such systems to scan postcodes before then. So, I’m not sure what’s new here?

]]> By: Kevin X http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899503 Kevin X Fri, 04 Jan 2008 21:47:48 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899503 The first thing that came to my mind is that I can finally copy and paste the emails from my friend's Facebook accounts. The image to text thing might work The first thing that came to my mind is that I can finally copy and paste the emails from my friend’s Facebook accounts. The image to text thing might work

]]> By: IanDanforth http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899447 IanDanforth Fri, 04 Jan 2008 20:54:30 +0000 http://www.techcrunch.com/2008/01/04/google-lodges-patent-for-reading-text-in-images-and-video/#comment-1899447 What they are doing is actually quite clever. First take a video of your target text, from, say, a passing car. Next determine the text area in each frame of that video, then use the slight variations between frames to enhance that area, and use standard OCR to read it. You wouldn't think that this is anything new, but in the AI world it is. Much of vision research has been stuck in a 2d world of flat, static images. Only recently has the power and importance of motion/time become apparent, and only very recently has it been used effectively. This is how your eyes work, you attend to a specific portion of a moving image and it is the moving object that your brain recognizes. I'd say they are two thirds of the way there, using motion to get more information out of an inevitably lossy camera, but will probably still shove the enhanced image off to a standard OCR engine. The final step will be a new type of OCR which really uses on motion. My bet is on Numenta for that. What they are doing is actually quite clever. First take a video of your target text, from, say, a passing car. Next determine the text area in each frame of that video, then use the slight variations between frames to enhance that area, and use standard OCR to read it.

You wouldn’t think that this is anything new, but in the AI world it is. Much of vision research has been stuck in a 2d world of flat, static images. Only recently has the power and importance of motion/time become apparent, and only very recently has it been used effectively. This is how your eyes work, you attend to a specific portion of a moving image and it is the moving object that your brain recognizes.

I’d say they are two thirds of the way there, using motion to get more information out of an inevitably lossy camera, but will probably still shove the enhanced image off to a standard OCR engine. The final step will be a new type of OCR which really uses on motion. My bet is on Numenta for that.

]]>