Introduction
In the field of digital photography, it is often difficult for an imaging device like a digital single-lens reflex camera to take an image in which all the objects are captured in focus. Typically, under a certain focal setting of optical lens, only the objects within the depth-of-field (DOF) have sharp appearance in the photograph while other objects are likely to be blurred. A popular technique to obtain an all-in-focus image is fusing multiple images of the same scene taken with different focal settings, which is known as multi-focus image fusion.
Aim
Aim of the project is to capture fully focused images with minimal specification smartphone camera.
Implementation
Results
Introduction
In the field of digital photography, it is often difficult for an imaging device like a digital single-lens reflex camera to take an image in which all the objects are captured in focus. Typically, under a certain focal setting of optical lens, only the objects within the depth-of-field (DOF) have sharp appearance in the photograph while other objects are likely to be blurred. A popular technique to obtain an all-in-focus image is fusing multiple images of the same scene taken with different focal settings, which is known as multi-focus image fusion.
Aim
Aim of the project is to capture fully focused images with minimal specification smartphone camera.
Implementation
- Obtained an all-in-focus image by fusing multiple images of the same scene taken with different focal settings of camera using Deep CNN as described in the paper by Yu Liu.
- Modified the network to make it as light as possible and written using Tensorflow library to build in android.
Results
Image captured with focus on lower region
|
Image captured with focus on upper region
|
Fully focused Image generated by our network
Project Contributors
- Kartik Paigwar | k.kartikpaigwar@gmail.com
- Kartik Sonu | kartiksonu39@gmail.com
Project Supervisor
- Prof. Shital Chiddarwar | shitalsc@mech.vnit.ac.in
