Joe Kohlmann & Nathalie Cheng
University of Wisconsin-Madison
CS534: Computational Photography
Spring 2011
Abstract

Our project idea fuses concepts from two research papers: "Colorization using Optimization" by Levin et al and "Fast Multiresolution Image Querying" by Jacobs et al.

Given a user's doodle (saved as a GIF with an indexed color table), the project recognizes the segments of the image drawn using the same color. It uses these color-grouped segments to query a database of images (as in Jacobs et al) based on shape alone (not color). The algorithm takes the resulting segment matches and colorizes them using the original doodle segment colors. Finally, it outputs the combined (and possibly blended) segments in a final image—a surreal recreation of the original doodle from real, color-shifted photographic data.

Imagine a doodle containing a green plain in the background, a blue sky, a yellow stick figure and a red car. Each segment of the image appears in a distinct color, so the algorithm extracts them, performs image matching queries with each, color corrects the matches, and blends the final image together from real images of a plain, a sky, a person, and a car. The photographic matches are all colorized to create a vivid realization of the original doodle.

-> ->

 

Paper and Code

Download our Paper (PDF)

Download the Code (ZIP)

Code Requirements:

The Matlab file ComposeDoodle.m implements Doodle Segment Querying and Colorization by Joe Kohlmann and Nathalie Cheng. This project uses code adapted from the following original authors:

We claim no rights to the original authors' works. We redistribute this code as part of our CS 534 final project for academic purposes only.