Access Restriction

Author Raman, Shanmuganathan ♦ Kanojia, Gagan
Source IIT Gandhinagar
Content type Text
Publisher IEEE
Language English
Subject Keyword Training ♦ Vegetation ♦ Apertures ♦ Cameras ♦ Image Reconstruction ♦ Lenses ♦ Principal Component Analysis
Abstract A photograph of the same scene can look different when captured using different camera settings. In this paper, we propose a novel technique to obtain the complete post-capture control over the focus and aperture settings of a traditional camera by acquiring small number of images. In this work, we tackle the problem of deciding which focus-aperture (F-A) combinations should be used to capture the input images, by solving it as a center selection problem. The images captured with the selected settings are then used to reconstruct the images for all possible F-A settings of a traditional camera. For the reconstruction of the images, we have used random regression forest. We show that the proposed approach provides an effective alternative for post-capture control in photography.
ISSN 10709908
Learning Resource Type Article
Publisher Date 2017-06-01
Journal IEEE Signal Processing Letters
Volume Number 24
Issue Number 6
Starting Page 751
Ending Page 755