Home > RESEARCH > Current Projects

Current Projects

Flow Visualization

This research focuses on designing and developing novel algorithms and techniques towards effective visual understanding of large and complex three-dimensional steady and unsteady flow fields. The project integrates and unifies a variety of concepts from geometric modeling, computer vision, and data mining to create robust visual characters and words from field lines for shape analysis and organization. We introduce novel interfaces and interactions to enable intuitive retrieval of partial field lines via textual and visual forms, and examination of hierarchical field lines and their spatiotemporal relationships in the transformed graph space. We also devise innovative streamline repositioning for focus+context viewing and automatic tour for examining hidden or occluded flow features to move from clutter to clarity in the visualization. Besides field lines, we are currently investigating the much less explored field surfaces and utilizing deep learning techniques to solve challenging problems in surface-based flow visualization.

Faculty: C. Wang

Scalable Benchmark

Mini-apps for Graph Engine Comparisons The last decade has seen the growth of extremely large, unstructured, and dynamic data sets, with the desire to extract not just specific facts also relationships between entities. Graphs have emerged as a valuable and productive paradigm for such expressing such problems, and there has been an explosion in new graph algorithms, graph query languages, and graph engines that perform such computations. This project is developing a suite of graph-based mini-apps that are directly relevant to real-world uses.

Faculty: P. Kogge

C-SWARM: Understanding future Exascale Computations

This project is part of Notre Dame's C-SWARM center, and is focused on determining the architectures (both hardware and software) that together will allow large multi-level codes such as being developed by C-SWARM to scale to Exascale levels.

Faculty: P. Kogge

Social Media Manipulation and Deterrence (funded by AFOSR)

Society is increasingly relying on the digitized, aggregated opinions of others to form opinions and make judgments. We therefore propose to study social news aggregation and commentary Web sites to investigate whether the use of these aggregates distorts opinions and decision-making. We study the effect that user-agents, including rouge or enemy actors, have in social news platforms, and we use this model to determine an appropriate deterrence strategy with the goal of making these types of systems resilient to influence attacks.

Faculty: T. Weninger

Principled Structure Discovery for Network Analysis (funded by NSF)

In this project we study a relationship between graph theory and formal language theory that allows for a Hyperedge Replacement Grammar (HRG) to be extracted from a graph. Like a context free grammar, but for graphs, the extracted HRG contains the precise building blocks of the network as well as the instructions by which these building blocks ought to be pieced together. In this project, we take the first steps towards reconciling the disparate fields of formal language and graph theory by asking incisive questions about the extraction, inference, and analysis of network patterns in a mathematically elegant and principled way.

Faculty: T. Weninger

Social Simulation of Online Human Behavior (selected for funding by DARPA)

The goal of this project is to create the first-of-its-kind cognitive agent simulation framework for studying multi-scale dynamics of social phenomena in online information environments. Individual agents’ behavior will be based on first-principles of human behavior validated through laboratory experiments and empirical analysis.

Faculty: T. Weninger

Variation in Accuracy of Biometrics Across Demographic Groups

Why and how do face recognition and other biometrics accuracy vary across race, gender and age? And what can be done about it?

Faculty: K. Bowyer

Detection of "Photo-shopped" Face Images 

Can photoshopped face images be automatically detected? How does the accuracy vary for different levels of photoshopping and different demographic groups?

Faculty: K. Bowyer

Detection of Iris Recognition Presentation Attacks

Presentation attacks can be made on iris recognition using contact lenses, printed images and other means. How reliably can different types of presentation attacks be detected? With a minimal change to current iris sensor operation?

Faculty:

Enabling Software Engineering Virtual Assistant Technology

The objective of this research project is to address key barriers in adapting natural language processing techniques to problems in creating virtual assistants for software engineering. Virtual assistants such as Siri, Cortana, and Alexa are claiming an increasing role in computing for everyday tasks, but multiple barriers prevent existing virtual assistant technology from being applied to software engineering tasks. The long-term goal of the project is that virtual assistants will improve productivity for software engineers.

Faculty: C. McMillan

Understanding Program Comprehension for Automated Software Documentation Generation

The objective of this research project is 1) to create a model of program comprehension for how software development professionals write software documentation, and 2) to use this model to design algorithms to automate the process of writing documentation. The process of writing documentation is a major expense in software development projects, and is often neglected. By automating key components of the process, this research helps programmers to avoid this expense and therefore to be more productive.

Faculty: C. McMillan

Surveillance Image and Video Analytics

This research is intended to develop suites of analytic technqiues for video acquired form surveillance camera networks.

Faculty: P. Flynn

DataSwarm: A Software Framework for Data Intensive Scientific Applications (NSF)

We are designing the next generation software framework for large scale applications that run on thousands of cores on clusters, clouds, and supercomputers. This has applications in high energy physics, neuroscience, and molecular dynamics for drug design.

Faculty: D. Thain

Software tool and methodology for enhancement of unidentified decedent systems with post-mortem automatic iris recognition (NIJ)

The purpose of this project is to deliver a complete methodology and the software that enhance unidentified decedent systems with a capability for comparisons of antemortem and postmortem iris images. The main research problem concerns novel methods, both related to computer vision and human examination, that allow for identification of deceased subjects based on their iris patterns.

Faculty: A. Czajka

Contactless Fingerprint Collection

In this project, the CVRL team explores methods of contactless fingerprint acquisition by cameras embedded in commercially available mobile phones, and compares the accuracy of fingerprint recognition achieved for images acquired by conventional (flat) optical sensors and contactless technologies.

Faculty: A. Czajka