Rose Vidal Mata, a CSE graduate student, has presented and defended her proposal,"Improving Scene Understanding in Adverse Scenarios" and has successfully passed her Oral Candidacy Exam.
Her advisers, Dr. Kevin Bowyer and Dr. Walter Scheirer, along with her committee members Dr. Jane Cleland-Huang, Dr. Patrick Flynn and Dr. Hilde Kuehne were in attendance.
Congratulations, Rose! This is an important milestone and we wish you continued success in your graduate program of study.
Aparna Bharati, a CSE PhD candidate, has successfully presented and defended her dissertation: "Vision and Learning-Based Methods for Scalable and Generalized Image Forensics".
Her adviser, Dr. Kevin Bowyer, along with her committee members Dr. Patrick Flynn, Dr. Nasir Memon, Dr. Anderson Rocha and Dr. Walter Scheirer were in attendance.
Congratulations, Aparna! We wish you continued success in all of your endeavors!
The fourth edition of the LivDet-Iris competition has been officially launched: http://www.iris2020.livdet.org. The iris presentation attack detection algorithms will be tested on the largest set of presentation attack instruments considered in all LivDet-Iris competitions to date -- we will use “classic” PAIs, such as textured contact lenses and paper printouts, and more “exotic” fakes, such as prosthetic eyes (with and without contact lenses), irises displayed on Kindle and … cadaver eyes. Algorithms can be submitted to the organizers for evaluations, or run directly on the BEAT platform (https://www.beat-eu.org).
The competition is part of the IJCB 2020 (https://ieee-biometrics.org/ijcb2020/) . Designers of the most accurate methods will be invited to co-author a research paper submitted to IJCB 2020. This is a joint effort of the CVRL @ University of Notre Dame, Clarkson University, Warsaw University of Technology (Poland), Medical University of Warsaw (Poland) and Idiap Research Institute (Switzerland).
Join the efforts of making iris recognition more secure!
Sophia Abraham and Lucas Barbosa Parzianello, both first year graduate students and members of the Computer Vision Lab, were recognized with the Honorable Mention Teaching Assistants Award given by the Computer Science and Engineering Department. This award is to recognize 1st year Teaching Assistants who have gone above and beyond their assigned duties and have shown a dedication to student learning.
Walter J. Scheirer, assistant professor of computer science and engineering, has received a 2020 National Science Foundation Early Career Development Award. The award is the highest honor given by the U.S. government to young faculty members in engineering and science.
Scheirer's research interests encompass computer vision, machine learning, biometrics and digital humanities. His CAREER project, titled "Learning at the Edge: An Extreme Value Theory for Visual Recognition," focuses on the development of new biologically-inspired models of visual recognition for artificial intelligence--how neuronal systems can identify and categorize environmental stimuli similar to humans. These models could significantly impact industry applications, such as self-driving cars and assistive technologies for the disabled. Basic science areas, such as vision science, psychology and neuroscience, also could benefit.
“It’s amazing when you consider that the human brain can take a flood of very complex information from the world around it, rapidly and accurately extracting meaning from all five senses in milliseconds,” said Scheirer. “The brain automatically adapts itself to the input it receives. That’s the secret we want to tap into as we approach machine learning for computer vision.”
In addition to the focus on research, CAREER projects contain educational components for training future generations. Scheirer will develop workshops on biologically consistent vision for researchers and graduate students. He also will create curricula featuring hands-on research opportunities that will be integrated into undergraduate courses.
Prior to joining the University in 2015, Scheirer served as a research associate and postdoctoral fellow at Harvard University, an assistant professor adjoint at the University of Colorado at Colorado Springs and the director of research and development at Securics, Inc.
He holds four patents and is a member of the Alliance of Digital Humanities Organizations, Institute of Electrical and Electronics Engineers (IEEE), IEEE Computer Society, IEEE Signal Processing Society, Society of Catholic Scientists and Society for Neuroscience.
Researchers at the University of Notre Dame are using artificial intelligence to develop an early warning system that will identify manipulated images, deepfake videos and disinformation online. The project is an effort to combat the rise of coordinated social media campaigns to incite violence, sew discord and threaten the integrity of democratic elections.
The scalable, automated system uses content-based image retrieval and applies computer vision-based techniques to root out political memes from multiple social networks.
“Memes are easy to create and even easier to share,” said Tim Weninger, associate professor in the Department of Computer Science and Engineering at Notre Dame. “When it comes to political memes, these can be used to help get out the vote, but they can also be used to spread inaccurate information and cause harm.”
Weninger, along with Walter Scheirer, an assistant professor in the Department of Computer Science and Engineering at Notre Dame, and members of the research team collected more than two million images and content from various sources on Twitter and Instagram related to the 2019 general election in Indonesia. The results of that election, in which the left-leaning, centrist incumbent garnered a majority vote over the conservative, populist candidate, sparked a wave of violent protests that left eight people dead and hundreds injured. Their study found both spontaneous and coordinated campaigns with the intent to influence the election and incite violence.
Those campaigns consisted of manipulated images exhibiting false claims and misrepresentation of incidents, logos belonging to legitimate news sources being used on fabricated news stories and memes created with the intent to provoke citizens and supporters of both parties.
While the ramifications of such campaigns were evident in the case of the Indonesian general election, the threat to democratic elections in the West already exists. The research team at Notre Dame, comprised of digital forensics experts and specialists in peace studies, said they are developing the system to flag manipulated content to prevent violence, and to warn journalists or election monitors of potential threats in real time.
The system, which is in the research and development phase, would be scalable to provide users with tailored options for monitoring content. While many challenges remain, such as determining an optimal means of scaling up data ingestion and processing for quick turnaround, Scheirer said the system is currently being evaluated for transition to operational use.
Development is not too far behind when it comes to the possibility of monitoring the 2020 general election in the United States, he said, and their team is already collecting relevant data.
“The disinformation age is here,” said Scheirer. “A deepfake replacing actors in a popular film might seem fun and lighthearted but imagine a video or a meme created for the sole purpose of pitting one world leader against another — saying words they didn’t actually say. Imagine how quickly that content could be shared and spread across platforms. Consider the consequences of those actions.”
Weninger, Scheirer and Michael Yankoski, a doctoral candidate in theology and peace studies at Notre Dame’s Kroc Institute for International Peace Studies, recently described the system in the Bulletin of the Atomic Scientists.
Scheirer is also an incoming faculty fellow at Notre Dame’s Institute for Advanced Study focusing on visual media and trust. Co-authors of the study include Pamela Bilo Thomas, Joel Brogan, Daniel Moreira, Pascal Phoa and William Theisen, all at Notre Dame. The Defense Advanced Research Projects Agency (DARPA), Air Force Research Laboratory (AFRL) and the United States Agency for International Development funded the study.
— Jessica Sieff, Notre Dame Media Relations
Amy Li, a PhD candidate, has successfully presented and defended her dissertation: "Studying Unconstrained Degraded Face Recognition and Redaction with Application in Real Surveillance Environment" and has passed her dissertation defense.
Her adviser, Dr. Patrick Flynn, along with committee members Dr. Kevin Bowyer, Dr. Domingo Mery and Dr. Walter Scheirer were in attendance.
Congratulations Amy! This is a significant accomplishment and we wish you all the best and continued success in all of your endeavors.
Kevin W. Bowyer, the Schubmehl-Prein Professor in the Department of Computer Science and Engineering at the University of Notre Dame, has been named a fellow of the American Association for the Advancement of Science (AAAS) for distinguished contributions to the field of computer vision and pattern recognition, biometrics, object recognition and data science.
Bowyer’s research has most recently focused on media forensics, on understanding issues of demographic fairness and bias in face recognition technology, and on developing iris recognition technology to more accurately identify potential threats. His work in media forensics is focused on creating algorithms that aim to detect if an image is original or has been altered. His work on demographic fairness of face recognition technology has explored how face recognition accuracy is different for men and women, and for Caucasians and African-Americans.
Election as an AAAS fellow is an honor bestowed upon members by their peers. Fellows will be recognized for their contributions to science and technology during the AAAS Annual meeting on Feb. 15.
— Jessica Sieff, Media Relations
Bingyu Shen, a CSE graduate student, has successfully presented and defended her proposal: "Proactive Storage Management for High-Throughput Scientific Workflows" and has passed her Oral Candidacy Exam.
Her adviser, Dr. Walter Scheirer, and committee members Dr. David Chiang, Dr. Adam Czajka and Dr. Brian Page were in attendance.
Congratulations, Bingyu!. This is an important milestone and we wish you continued success in your PhD program of study.
Brandon RichardWebster has been award a Fulbright Futures Scholarship. This 10 month award will take Brandon to Queensland University of Technology where he will work with a team to aid farmers in the detection and early eradication of an invasive grass which can devastate pasture productivity and increase the risk of wildfires. His research will include the collection of aerial video footage, conducting a field study, and developing a psychophysics driven machine learning algorithm which can be deployed on an unmanned aerial vehicle (UAV).
For more on the Fulbright Futures Scholarship visit the Fulbright Program's website.
Congratulations to Joel Brogan, a CSE candidate, for successfully presenting and defending his dissertation: “Advancing Biometrics and Image Forensics through Vision and Learning Systems".
His advisers, Dr. Kevin Bowyer and Dr. Walter Scheirer, along with his committee members Dr. Adam Czajka, Dr. Edward Delp and Dr. Patrick Flynn were in attendance.
Joel has passed his dissertation defense and will graduate in August with his PhD degree.
We wish Joel continued success in all of future his endeavors!
Congratulations to Sreya Banerjee on her successful presentation and defense of her proposal titled; "A Study on Biologically-Inspired Recognition Using Multi-platform & Multi-modal Data"
Her adviser, Dr. Walter Scheirer, and committee members Dr. Kevin Bowyer, Dr. Patrick Flynn and Dr. Lei Li were in attendance for her exam. She has passed the Oral Candidacy and is now officially a PhD candidate.
This is an important milestone and we wish Sreya continued success in our PhD graduate studies program!
Congratulations! Sandipan Banerjee, PhD
Sandipan Banerjee, a PhD candidate, has successfully presented and defended his dissertation; "Exploring the Effects of Frontalization & Data Synthesis on Face Recognition" and has passed his defense.
His advisers, Dr. Kevin Bowyer and Dr. Patrick Flynn, along with committee members Dr.Domingo Mery, Dr. Walter Scheirer and Dr. Chaoli Wang were in attendance.
Sanidpan will graduate with his PhD degree August 2019.
Congratulations, Sandipan! We wish you continued success in all of your edeavors.
Congratulations to Jeffery Kinnison on his successful presentation and defense of his proposal titled; “Large-Scale Non-Greedy Methods for Model Search". He has officially passed the Oral Candidacy exam.
His adiviser, Dr.Walter Scheirer, and committee members Dr. Adam Czajka, Dr. Christopher Sweet and Dr. Narayanan Kasthuri were in attendance.
This is an important milestone and we wish Jeffery continued success in our PhD graduate studies program!
Brandon RichardWesbster, a CSE graduate student, has successfully presented and defended his proposal; "Visual Psychophysics For Computer Vision" and has passed his Oral Candidacy exam.
His adviser, Dr. Walter Scheirer, and committee members Dr. Adam Czajka, Dr. Patrick Flynn and Dr. Michael Milford were in attendance.
The Oral Candidacy exam is an important milestone. We congratulate Brandon on this achievement and wish him continued success!
Congratulations to Nathan Blanchard, PhD.!
Nathan Blanchard a PhD candidate, has successfully presented and defended his dissertation: "Quantifying Internal Representation for Use in Model Search" and has passed his defense.
His adviser, Dr. Walter Scheirer, and committee members Dr. Kevin Bowyer, Dr. Patrick Flynn, Dr. Christopher Forstall and Dr. Sean Kelly were in attendance.
Congratulations Nathan! We wish you continued success in all of your endeavors.
"Visual Psychophysics for Making Face Recognition Algorithms More Explainable" (Brandon RichardWebster, So Yon Kwon, Christopher Clarizio, Samuel E. Anthony, Walter J. Scheirer) was accepted at the 2018 European Conference on Computer Vision.
Congratulations to Ali Shahbazi for successfully defending his dissertation "Computer Vision-based Approaches to Neural Circuit Tracing at Scale"!