N
Nalini K. Ratha
Researcher at IBM
Publications - 230
Citations - 13245
Nalini K. Ratha is an academic researcher from IBM. The author has contributed to research in topics: Biometrics & Fingerprint recognition. The author has an hindex of 50, co-authored 216 publications receiving 12290 citations. Previous affiliations of Nalini K. Ratha include Michigan State University & University at Buffalo.
Papers
More filters
Patent
Identifying artificial artifacts in input data to detect adversarial attacks
TL;DR: In this paper, a neural network processes adversarial input data and layer-wise comparison logic compares, for each intermediate layer of the neural network, a response generated by the intermediate layer based on processing the adversarial inputs, to the mean response associated with intermediate layer, to thereby generate a distance metric for the intermediate layers.
Book ChapterDOI
A comparative performance analysis of JPEG 2000 vs. WSQ for fingerprint image compression
TL;DR: The performance analysis is based on three public databases of fingerprint images acquired using different imaging sensors and shows that JPEG 2000 provides better compression with less impact on the overall system accuracy performance.
Patent
Method for bio-metric-based authentication in radio communication for access control
Rudolf Maarten Bolle,Sharathchandra U. Pankanti,Nalini K. Ratha,Louise Nanzu Sharon,Barton A. Smith,Thomas G. Zimmerman,シャラトチャンドラ・パンカンティ,シャロン・ルイーズ・ナンズ,トーマス・ガスリー・ジューマン,ナリニ・カンタ・ラタ,バートン・アレン・スミス,ルドルフ・マールテン・ボッレ +11 more
TL;DR: In this article, a system and a method for authenticating a user by a radio communication, using an acquired bio-metric (for example fingerprint) and a biometric template stored locally, was proposed.
Proceedings ArticleDOI
A Gradient Descent Approach for Multi-modal Biometric Identification
TL;DR: This paper proposes a score based fusion scheme tailored for identification applications that uses a gradient descent method to learn weights for each modality such that weighted sum of genuine scores is larger than the weightedsum of all the impostor scores.
Posted Content
Heterogeneity Aware Deep Embedding for Mobile Periocular Recognition.
TL;DR: In this article, a novel heterogeneity aware loss function within a deep learning framework was proposed to address the heterogeneous challenge of recognizing biometric patterns in unconstrained environment including variations in mobile camera sensors, illumination conditions, and capture distance.