A question was posed to Google's Gary Illye's on Twitter if Google's crawler and indexer understands the text embedded in an image, maybe through OCR or other techniques. I am surprised to hear Gary say no.
Here is the set of tweets, maybe I am misinterpreting it:
@Web4Raw I say no
— Gary Illyes (@methode) March 15, 2016
Back in 2008, Google filed a patent to recognize text in an image. Truth is, text in an image is easier for Google to understand than other attributes they try to understand. Google does some insane image interpretation to group faces, places, colors, and so so many other things that makes you sometimes go wow - how does Google do that.
So for Google not to be able to understand the text embedded in an image, makes me wonder.
What do you think?
Forum discussion at Twitter.
