How to detect text region from a document image?

I have a document image, which might be a newspaper or magazine. For example, a scanned newspaper. I want to remove all/most text and keep images in the document. Anyone know how to detect text region in the document? Below is an example. Thanks in advance!

Answer 1

[Dima Lisin]

Try using the ocr function in the Computer Vision System Toolbox.

[Leung]

It needs the computer vision toolbox and it only supports English language. I want to detect text region other than english words.

Any other ideas? Thanks!

[Dima Lisin]

Actually, ocr supports many languages. But it does require the Computer Vision System Toolbox.

Answer 2

[Image Analyst]

If you don't want to use the Computer Vision System Toolbox, see this: http://www.visionbib.com/bibliography/contentschar.html#OCR,%20Document%20Analysis%20and%20Character%20Recognition%20Systems for a bunch of algorithms that can handle it in many languages. You'd have to write the code for those papers - we don't have any code for any of them.

[Leung]

Thanks! I will take a look at it, are there other simple methods to do this? As I don't need to know the content of the text, I only need to know the location of the text region. :_)