Research team wins NSF Entrepreneurship Grant for AI-Guided Imaging

The research team includes, from left, Yihong Feng, Swarna Sethu, and Dongye Wang.

Fred Miller

The research team includes, from left, Yihong Feng, Swarna Sethu, and Dongye Wang.

The National Science Foundation has awarded an Innovation Team Entrepreneurship Grant to the Arkansas Agricultural Experiment Station Research Team for a machine vision system developed using AI-guided imaging.

The $50,000 grant supports participation in NSF’s I-Corps program. It is designed to help technology developers translate promising ideas and technologies from the lab to market, increase the economic competitiveness of the United States and encourage collaboration between academia and industry, according to NSF’s I-Corp website.

The team in the Department of Biological and Agricultural Engineering includes Assistant Professor Dongye Wang, as principal investigator. Swarna Sethu, Postdoctoral Researcher, as Leading Entrepreneur; graduate student Yihong Feng as technical lead; and Wale Obadimu, Website Reliability Engineer at LinkedIn, as an industry leader.

Sethu said the NSF I-Corps program uses experiential education to help researchers gain insight into entrepreneurship, starting a business or industry requirements and challenges. Participants learn practical skills in communicating with clients, asking the right questions and how to find partners to help launch startup ideas.

As part of the I-Corps program, Sethu participated in a seven-week group program, which is a training seminar to develop entrepreneurial skills. She interviews industry and consumer advisors to help identify promising markets for the technology.

With funding from an initial NSF grant, Wang developed the idea of ​​teaching an artificial intelligence program to discern human responses to digital images of food products. The team used machine learning technology to teach an AI-guided digital imaging system to predict whether or not consumers would find food products acceptable.

Sethu photographs the products under color-changing lights to change the appearance of the foods.

The team collaborated with Han-Seok Seo, an associate professor of sensory science in the Experimental Station’s food science department, to connect the machine’s predictions to a consumer panel of people trained to rate food products in his lab. Sethu said 75 participants took part in the study.

Wang said that the AI-guided system now has a high reliability rate in predicting consumer acceptance. “It can provide solid data to support its predictions,” he said.

Wang said the system can also help consumers who shop on retailers’ mobile apps by accurately presenting product images in the most attractive lighting. “It can create an enhanced visual experience for consumers.”

The predictive technology is almost ready, Wang said, but they have to develop a marketable application for it. He said the team may also be looking at ways to adapt the technology to other retail products.

To learn more about the Department of Agricultural Research, visit the Arkansas Agricultural Experiment Station website: Follow us on Twitter at @employee and on Instagram at @ArkAgResearch. To learn more about the Department of Agriculture, visit Follow us on Twitter at @employee.

About the Agriculture Division: The mission of the University of Arkansas Department of Agriculture is to strengthen agriculture, communities, and families by connecting authoritative research with the adoption of best practices. Through the Agricultural Experiment Station and Cooperative Extension Service, the Department of Agriculture conducts research and extension work within the country’s historic land grant education system. The Department of Agriculture is one of 20 entities within the University of Arkansas system. It has offices in all 75 counties in Arkansas and faculty in five campuses. The Department of Agriculture at the University of Arkansas offers all extension and research programs, services, and research without regard to race, color, sex, gender identity, sexual orientation, national origin, religion, age, disability, marital or veteran status, genetic information, or other legally protected status, which is Affirmative Action / Equal Opportunity Employer.

Leave a Comment