Abstract
The goal of this project is to highlight differences between two contrasting images taken of the same scene at different points in history or at different times of day by combining them to create a visual timeline output image. This will be accomplished by compositing two input images into one blended image where each image takes up about half of the space in the final processed image. In order to combine the images, we will use the Laplacian Pyramid Blending method to seamlessly combine the images, creating a composite output image of the two input images in the middle and leaving the originals unchanged further from the center.
Introduction & Motivation
Image compositing and blending has been around quite some time, but the idea of blending images of same scene at different times of day or even decades has been relatively new. The technique of image compositing was invented in the 1880s after a suggestion for registering photographs of human faces on the two eyes to create an average photograph of all those in the group. With the advancement of the computer technology in the 1990s, image compositing technique has greatly improved using computer graphics software.
Previous works done blending images of the same scene at different times are very limited and were done manually, mostly using Photoshop. In this project, image compositing and blending will be done using Matlab programming. There are many techniques for blending images, this project will use Laplacian Pyramid Blending. This content-based blending technique using edge features, hides seams but preserve sharp details in order to produce an output visual timeline photo that transitions discretely between the old and the new photo.