Computer Science Lecturer
University of North Carolina Wilmington, College of Arts & Sciences
Ben Barbour is a Computer Science Lecturer for UNCW, Research Associate in the Instititue for Interdisciplinary Identity Studies (I3S), and Lead Architect/Developer for Lapetus Solutions, Inc. His research involves developing advanced algorithms the domain of Facial Analytics and Biometrics.
University of North Carolina Wilmington, College of Arts & Sciences
Miller-Motte College, Information Technology
Master of Computer Science and Information Systems
University of North Carolina Wilmington
Bachelor of Science in Computer Science
University of North Carolina Wilmington
The main contribution of this paper is to introduce DASM - Dynamic Active Shape Models, an open source software for the automatic detection of fiducial points on objects for subsequent registration, to the research community. DASM leverages the tremendous work of STASM, a well known software library for automatic detection of points on faces. In this work we compare DASM to other well-known techniques for automatic face registration: Active Appearance Models (AAM) and Constrained Local Models (CLM). Further we show that DASM outperforms these techniques on a per registration-point error, average object error, and on cumulative error distribution. As a follow on, we show that DASM outperforms STASM v3.1 on model training and registration by leveraging open source libraries for computer vision (OpenCV v2.4) and threading/parallelism (OpenMP). The improvements in speed and performance of DASM allows for extremely dense registration, 252 points on the face, in video applications.
The purpose of this paper is to introduce a tool that provides a GUI for generating a ground truth for landmark positions for 2D images used in computer vision applications. Further, we demonstrate via a case study that this tool greatly improves manual landmarking in the case of extremely dense (more than 250 points per images) annotation of face images with a factor of two speed up. Moreover the tool incorporates workflow technology capable of allowing multiple land-markers to work on the same set of images and for quality assurance checks. We are in the process of making this tool freely available to researchers from academia.
Computer science instructors often rely on the final version of a program for assessment and feedback. This ignores the process the student used to arrive at the final program. When the instructor has the ability to observe real-time development progress of each student, they are better equipped to provide appropriate and timely feedback. CodeWave, a software program developed at the University of North Carolina Wilmington looks to alleviate these issues.
CodeWave is a real-time, collaborative Integrated Development Environment with traditional features such as syntax highlighting and non-traditional features such as integrated messaging and logged playback. CodeWave enhances productivity by integrating many common tools students and instructors use during the programming process. Communication is effortless and allows a user to specify a point in the code as a link in the message body. Log playback provides the ability to review the entire development process. In this paper, we describe the software program we developed to enhance learning in computer science programming courses.
Face characteristics can be used for gender identification and age estimation in a wide range of biometric applications. The emerging field of soft biometrics is exploring exciting new questions about biometric traits. Soft biometrics for automated gender identification and age estimation have potential applications in a multitude of areas.
Sammi is a 3-Dimensional Virtual Human Information Kiosk for use by the Computer Science department at The University of North Carolina Wilmington. Sammi's purpose is to provide information to users about UNCW's Computer Science department, including the faculty, staff, building, and courses offered. She is also able to answer general questions about UNCW and has the ability to carry on an intelligent conversation when the statements or questions are outside the domain of UNCW. Sammi, once fully functional, is to be located in the Computer Information Systems Building. The majority of users will be UNCW students. Sammi will take speech as input and will output speech and graphics (such as maps and diagrams). We describe the design, development, and architecture of Sammi and will discuss the accuracy of her responses to questions from users in our field test.
Prerequisites: CSC 231 and CSC 242. The theory and application of inter-computer communications. Local-area and wide-area networks; data transmission and error correction; OSI and TCP/IP layering protocols; Ethernet, token ring, token bus, and other network technologies; network topologies; the client-server model; bridges and multi-protocol routers; the Internet. Applications include electronic funds transfer and distributed databases.
Prerequisite: CSC 242 and CSC 231. An introduction to theoretical computer science. Topics include regular expression and finite state concepts; basic automata theory; formal grammars and languages; computability; Turing machines; elementary recursive function theory.
You can find me at my office located on the second floor of the CIS building in room 2025. This is a shared office, please visit during my posted office hours.
I work during the day the Center for Innovation and Entreprenuership (CIE) located next to the Cookout offices off College Rd.
I am available by appointment to meet at my work office as needed but prefer office hours in the CIS building!