"It is an enriching experience for me to observe people as they come to recognize something for the first time."Read More
UAlbany Computer Science Professor Receives Prestigious NSF Award to Develop New Tools to Detect Fake Digital Images
$500,000 National Science Foundation award will also help researchers better understand images, vision
This altered photo, used as an Internet hoax, is a composite of a U.S. Air Force photo of an HH-60G Pave Hawk helicopter during a rescue diver training session in San Francisco Bay and a still shot of a great white shark breaching the ocean surface.
ALBANY, N.Y. (April 27, 2010) -- University at Albany Computer Science Professor Siwei Lyu is the recipient of a highly competitive Faculty Early Career Development (CAREER) Award from the National Science Foundation (NSF) to develop new methods to detect digital images that have been altered. The five-year, $500,000, award recognizes Professor Lyu’s accomplishments and potential, and is intended to serve as a firm foundation for a lifetime of leadership in education and research. His project, "A New Statistical Framework for Natural Images with Applications in Vision," examines a new mathematics-based language to describe images and build models to more effectively capture the statistical properties of natural images.
The Faculty Early Career Development Program offers the National Science Foundation's most prestigious awards in support of the early career-development activities of teacher-scholars who most effectively integrate research and education in their work. The awards support a select group of junior faculty across the nation who exhibit exceptional promise for combining outstanding research with excellent teaching.
“Professor Lyu’s prestigious NSF CAREER research award is recognition of his leading-edge contributions in this important area. We are confident his research will advance efforts to determine the legitimacy of digital images and have many applications in our information society,” said UAlbany President George M. Philip.
One important part of Professor Lyu’s project is to develop new tools to detect doctored images. With the advancement of digital cameras, the Internet, and software such as Adobe Photoshop, digital image forgeries have become more prevalent. These doctored images challenge the status of photographs as definitive records of events, especially when images are presented as documentary or legal evidence. Professor Lyu has been involved in several ground-breaking research projects related to forensic authentication and analysis of digital images.
His CAREER project will further explore this new frontier, taking advantage of new statistical models and tools. The aim is to identify images that have been tampered with—or “photo-chopped”—and expose the tampered regions. Lyu will pursue collaborations with forensic investigators at the New York State Police Department Forensic Investigation Unit to apply some of the cutting-edge techniques in digital image forensics to practical criminal investigations. More information about this project can be found at Lyu’s Web site.
Lyu’s project also looks at fundamental questions in the study of images and vision: What are the building blocks of images we encounter in the everyday real world? What is the best language to describe them?
“The wisdom of the past two decades has been that images are formed by adding and subtracting simple units. For instance, by adding up images of trees, you should get an image of a forest,” said Lyu. “But this is not the way images from our physical world are created. You put images of trees on top of each other based on how close they are from you to get an image of a forest, and this nonlinear process is very different from simply adding them together."
By providing new statistical representations for images, Lyu’s work will have many far-reaching impacts, including better understanding of biological vision, new tools to compress images for faster transmission, new ways to restore corrupted and imperfect images, and automatic detection and recognition of objects in an image.
“Digital images are so important and pervasive in our society, and Professor Lyu’s work is critical to guaranteeing their credibility,” said College of Computing and Information Dean Peter Bloniarz. “Not only does he do cutting-edge research, but he also engages students in a way that prepares them to contribute to our digital economy right from the day they graduate.”
The College of Computing and Information at the University at Albany is headquartered on the Harriman Research and Technology Park. We prepare UAlbany students to succeed in the information-rich world they will inhabit, and through our research we help create that world. At CCI, we believe in "Empowering People through Information."
For more news, subscribe to UAlbany's RSS headline feeds
Educationally and culturally, the University at Albany-SUNY puts "The World Within Reach" for its 18,000 students. An internationally recognized research university with 58 undergraduate majors and 128 graduate degree programs, UAlbany is a leader among all New York State colleges and universities in such diverse fields as public policy, nanotechnology and criminal justice. With a curriculum enhanced by 300 study-abroad opportunities, UAlbany launches great careers. For more information about this globally ranked University, visit www.albany.edu. For UAlbany's extensive roster of faculty experts, visit www.albany.edu/news/experts.shtml.