(Archived) Request: Use text from pictures

[robertcurtis 0]

Evernote's ability to recognise text is very good, as is the ability to search for text within pictures.

However, what would make this feature even more useful would be the ability to use this text - i.e. copy and paste into a text document, note or email. A good example would be taking a picture of a business card, then being able to use the email address to send an email rather than type it out.

[engberg 89]

Our search technology isn't the same as simple Optical Character Recognition (OCR), since we're not just generating a single match for every word. Instead, we analyze the image to generate a weighted set of possibilities for each region so that we may match both "clue" and "due" against a word, if the letters are close together.

As a result, there isn't a simple text representation.

[robertcurtis 0]

That's interesting.

The reason I mention all of this is because to me (and people I have shown the app to) the ability to recognise text is undeniably cool, and often results in smiles. However, it doesn't appear genuinely useful (you'll have to excuse the fact that I'm new to Evernote) given what you might want to do with images that contain text.

For myself, having the ability to use the text makes Evernote something I would use frequently, rather than having just downloaded it to have a play with the text recognition engine; more specifically referring to use in a mobile context (e.g. iPhone) where OCR would be faster/easier than typing.

Obviously, from what you say this is probably outside the scope of what you intended for the app.

[engberg 89]

I think the key (from our perspective) is that we keep the original image, and we make it easy for you to find that image. Then you can just get what you want by looking at the image. This is a little different from "OCR" approaches that take a perfect quality scan, extract the text, and then throw away the image. We're assuming that not all of your pictures are perfect, so the most useful thing we can do is help you find the image itself.