Hello,
I have displayed a partial chessboard on a glass surface using a DLP projector. I have used my Raspberry pi camera to capture the virtual image of the checkerboard on the glass surface.
The quality of the resulting image is very poor (due to flickering and noise). I want to use OpenCV to enhance my image quialty so that it atleast has the same grayscale value as the original.
Currently the image is so poor that when i convert it into grayscale, most of the line information is lost.
Is there any way that we can enhance the quailty of the virtual image to look similar to the original image? fiddling with the birghtness or contrast of the image?
What I have tried:
i tried
fastNlMeansDenoising
Denoising — OpenCV 2.4.13.2 documentation[
^]
but then my code gets stuck in an infinite loop when i try my image alignment algorithms on the resulting image.
i have also tried the following sequence
grayscale > Gaussain blur (kernel size 2) > addweighted of gray scale and gaussian > erode > dilate.
The resulting image still has poor quailty
I have also tried histogram equilization, but the result doesnt improve