Grainy GreyScale Image?

The first image is a screenshot of some data in jpeg format. I converted this into greyscale and applied medfilt2() to try to reduce noise in image 2. In Image 3 I converted all the white points to red and it shows there is alot more than I thought there would be.

I am basically trying to convert the screenshot into a graph where I can interpret the data.

Are any ways to improve the process?

Thanks

Answer 1

[Rajani Mishra]

To remove noise from image you can try different noise removal functions in MATLAB.

You can find filtering functions here : https://www.mathworks.com/help/images/noise-removal.html

You can also try Bilateral Filtering if above functions fails to give desired results. Find its implementation here: https://www.mathworks.com/matlabcentral/fileexchange/12191-bilateral-filtering

You can consider extracting curvature of the image using bwboundaries, you can find code for the same here : https://www.mathworks.com/matlabcentral/answers/164349-how-to-calculate-the-curvature-of-a-boundaries-in-binary-images

I have tried the same code for your image, and I have attached the result after passing your image as an input.

Hope this helps!