Date of Award:

8-2025

Document Type:

Thesis

Degree Name:

Master of Science (MS)

Department:

Computer Science

Committee Chair(s)

Steve Petruzza

Committee

Steve Petruzza

Committee

Isaac Cho

Committee

Alfonso Torres

Abstract

When creating large stitched images, like those used in maps made from aerial photos, it’s important to make sure the seams between individual pictures aren’t visible. This process, known as color blending, helps smooth out differences in lighting or weather across the images. But blending very large images, such as those made from many high-resolution aerial photos, can require huge amounts of memory, making it hard to do on a typical computer.

In this work, we developed a method that breaks the problem into smaller pieces, so only a small part of the image needs to be worked on at a time. This makes it possible to blend very large images without needing an expensive supercomputer. Our approach uses a low-resolution version of the full image to help guide the blending of each small part, ensuring the final result looks smooth and natural. We also designed new techniques to make the process faster and more efficient, depending on how much blending is needed in each region of the image.

Checksum

51c7288d235af468386209a40da93ef4

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS