T
Terrance E. Boult
Researcher at University of Colorado Colorado Springs
Publications - 285
Citations - 13190
Terrance E. Boult is an academic researcher from University of Colorado Colorado Springs. The author has contributed to research in topics: Facial recognition system & Biometrics. The author has an hindex of 51, co-authored 274 publications receiving 10853 citations. Previous affiliations of Terrance E. Boult include Columbia University & King Abdulaziz University.
Papers
More filters
Proceedings ArticleDOI
Are Accuracy and Robustness Correlated
TL;DR: It is demonstrated that better machine learning models are less vulnerable to adversarial examples, and cross-model adversarial portability is found to be mostly transferable across similar network topologies.
Posted Content
Reducing Network Agnostophobia
TL;DR: In this paper, Entropic Open-Set and Objectosphere losses are proposed to maximize entropy for unknown inputs while increasing separation in deep feature space by modifying magnitudes of known and unknown samples.
Patent
Adaptive imaging using digital light processing
Shree K. Nayar,Terrance E. Boult +1 more
TL;DR: In this paper, a system for the adaptive imaging of a scene includes a digital light processing apparatus (150) adapted for controllably reflecting an image of the scene in at least a first direction to thereby reflect an intensity modulated image along at least the first direction.
Patent
Bio-cryptography: secure cryptographic protocols with bipartite biotokens
TL;DR: In this article, various transformation approaches are described that provide a secure means for transforming a stored or live, secure biometric-based identity token, embedding data into such tokens and biometricbased matching to both verify the user's identity and recover the embedded data.
Proceedings ArticleDOI
Detecting and classifying scars, marks, and tattoos found in the wild
TL;DR: This work introduces a new methodology for detecting and classifying scars, marks and tattoos found in unconstrained imagery typical of forensics scenarios, and considers the “open set” nature of the classification problem, and describes an appropriate machine learning methodology that addresses it.