User profiles for Walter J. Scheirer
Walter ScheirerDennis O. Doughty Collegiate Professor of Engineering Verified email at nd.edu Cited by 9386 |
Toward open set recognition
WJ Scheirer, A de Rezende Rocha… - IEEE transactions on …, 2012 - ieeexplore.ieee.org
To date, almost all experimental evaluations of machine learning-based recognition algorithms
in computer vision have taken the form of “closed set” recognition, whereby all testing …
in computer vision have taken the form of “closed set” recognition, whereby all testing …
Probability models for open set recognition
Real-world tasks in computer vision often touch upon open set recognition: multi-class
recognition with incomplete knowledge of the world and many unknown inputs. Recent work on …
recognition with incomplete knowledge of the world and many unknown inputs. Recent work on …
Multi-class open set recognition using probability of inclusion
… This paper extends the recent statistical learning work of Scheirer et al. [43,42], which is
limited to closed set problems. Our extension directly models the probability of inclusion for open …
limited to closed set problems. Our extension directly models the probability of inclusion for open …
Cracking fuzzy vaults and biometric encryption
WJ Scheirer, TE Boult - 2007 Biometrics Symposium, 2007 - ieeexplore.ieee.org
This paper is a security analysis of leading privacy enhanced technologies (PETs) for
biometrics including biometric fuzzy vaults (BFV) and biometric encryption (BE). The lack of …
biometrics including biometric fuzzy vaults (BFV) and biometric encryption (BE). The lack of …
The extreme value machine
It is often desirable to be able to recognize when inputs to a recognition function learned in
a supervised manner correspond to classes unseen at training time. With this ability, new …
a supervised manner correspond to classes unseen at training time. With this ability, new …
Advancing image understanding in poor visibility environments: A collective benchmark study
Existing enhancement methods are empirically expected to help the high-level end computer
vision task: however, that is observed to not always be the case in practice. We focus on …
vision task: however, that is observed to not always be the case in practice. We focus on …
Meta-recognition: The theory and practice of recognition score analysis
WJ Scheirer, A Rocha, RJ Micheals… - IEEE transactions on …, 2011 - ieeexplore.ieee.org
In this paper, we define meta-recognition, a performance prediction method for recognition
algorithms, and examine the theoretical basis for its postrecognition score analysis form …
algorithms, and examine the theoretical basis for its postrecognition score analysis form …
Authorship attribution for social media forensics
A Rocha, WJ Scheirer, CW Forstall… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
The veil of anonymity provided by smartphones with pre-paid SIM cards, public Wi-Fi hotspots,
and distributed networks like Tor has drastically complicated the task of identifying users …
and distributed networks like Tor has drastically complicated the task of identifying users …
Multi-attribute spaces: Calibration for attribute fusion and similarity search
Recent work has shown that visual attributes are a powerful approach for applications such
as recognition, image description and retrieval. However, fusing multiple attribute scores - as …
as recognition, image description and retrieval. However, fusing multiple attribute scores - as …
Revocable fingerprint biotokens: Accuracy and security analysis
TE Boult, WJ Scheirer… - 2007 IEEE Conference on …, 2007 - ieeexplore.ieee.org
This paper reviews the biometric dilemma, the pending threat that may limit the long-term
value of biometrics in security applications. Unlike passwords, if a biometric database is ever …
value of biometrics in security applications. Unlike passwords, if a biometric database is ever …