stub New Prototype Software Developed for Quilting Design - Unite.AI
Connect with us

Artificial Intelligence

New Prototype Software Developed for Quilting Design

Updated on
Image: Mackenzie Leake

A computer science graduate at Stanford University has developed new prototype software that can facilitate pattern-making for foundation paper piecing, which is a form of quilting. Paper piecing involves the use of a backing made of foundation paper to lay out and sew quilted designs. 

There are not many guidelines for developing a foundation paper piece quilt pattern, and the few that do exist are not enough for a successful result. This is what led Mackenzie Leake to set out and develop a new algorithm.

Leake is also a member of the lab of Maneesh Agrawala, Forest Baskett Professor of Computer Science and director of the Brown Institute for Media Innovation at Stanford. 

“Quilting has this rich tradition and people make these very personal, cherished heirlooms but paper piece quilting often requires that people work from patterns that other people designed,” said Leake. “So, we wanted to produce a digital tool that lets people design the patterns that they want to design without having to think through all of the geometry, ordering and constraints.”

The paper detailing the work was published and will be presented in August at the computer graphics conference SIGGRAPH 2021. 

Paper Piece Quilts

Leake says that the modern aesthetic and high level of control and precision is key to paper piece quilts. It follows a “sew and flip” action, meaning the pattern must be produced in a careful way.

If the pattern is executed poorly, it will suffer from loose pieces, holes, misplaced seams and designs that are impossible to finish. This all means quilters often have a hard time creating their own paper designs. 

Leake is the lead author of the published paper.

“The biggest challenge that we're tackling is letting people focus on the creative part and offload the mental energy of figuring out whether they can use this technique or not,” said Leake. “It's important to me that we're really aware and respectful of the way that people like to create and that we aren't over-automating that process.”

Prior to this new work, Leake designed a tool for improvisational quilting, which was presented at the human-computer interaction conference CHI in May.

Developing the Algorithm

The new algorithm is heavily based on a substantial theoretical foundation. Since the researchers could not rely on many existing guidelines, they had to first gain a deeper understanding of the piece-able aspect of the quilt paper, which then had to be put into mathematical terms.

The team discovered that they needed a hypergraph, which is a particular graph structure that can accommodate overlapping relationships between many data points. Through the use of a hypergraph, the researchers found a way to tell if a pattern will be paper piece-able. 

The prototype software enables users to sketch out a design, while the hypergraph-based algorithm determines what paper foundation patterns would make that design possible. 

“I didn't expect to be writing my computer science dissertation on quilting when I started,” said Leake. “But I found this really rich space of problems involving design and computation and traditional crafts, so there have been lots of different pieces we've been able to pull off and examine in that space.”

Co-authors for the paper included researchers from University of California, Berkeley and Cornell University.

Alex McFarland is a tech writer who covers the latest developments in artificial intelligence. He has worked with AI startups and publications across the globe.