Why do we convert grayscale to binary image in image processing

I am doing a project on hand recognition and in a paper that i read they have converted rgb to gray and gray to binary...

[Image Analyst]

Please post your image so we can see what you're talking about. Use the image icon above the edit box. It's best to have an image if you're going to give advice on image processing, wouldn't you agree?

Answer 1

[Walter Roberson]

Converting to binary is often used in order to find a Region Of Interest -- a portion of the image that is of interest for further processing. The intention is binary, "Yes, this pixel is of interest" or "No, this pixel is not of interest".

[Joseph Cheng]

Additionally in hand writing recognition you are not usually interested in rgb or gray scale images but those are the usual input images that are worked on (unless you have a electronic handwriting input device). As Walter Roberson says it simplifies the final image to written mark and background.

[Walter Roberson]

I think maybe Sumit is trying to recognize hands themselves (as in gesture recognition) rather than hand writing. Hard to be sure though.

[Joseph Cheng]

Oh, that would make sense

[David Young]

If you're trying to recognise the hands themselves, it may be very helpful to use the colour information - so it might be more successful to go from rgb to binary, selecting the pixels of interest according to where they lie in colour space.

[Sumit]

thanks for answers, currently i am doing literature survey for our presentation and implementation will be done in next semester.

Answer 2

[Image Analyst]

See my skin segmentation demo, attached below in blue.

Answer 3

[Youssef Khmou]

hi,

This transformation is useful in detecting blobs and reduces the computational complexity, however many other studies perform on the degree of colors like in skin detection like @Young pointed in his comment.