Abstract:
Brightfield microscopes cannot focus thick specimens due to their limited depth of field. A multi-focus fusion method is used to create an all-in-focus image from a z-stack of optically sectioned specimen images. Fusion methods cannot remove blur between optical sections in undersampled image stacks.
We propose a parameter-free Gaussian PSF model that estimates the all-in-focus image, depth map, and image plane sampling distances from the image sequence without knowledge of the z-stack acquisition.
In a maximum a posteriori framework, an iteratively reweighted least squares method estimates the image and an adaptive scaled gradient descent method estimates the depth map and sampling distances efficiently. The proposed method reduces fusion artifacts and recovers sharper edges in synthetic and real data.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
