R
Rupali Sandip Kute
Researcher at Massachusetts Institute of Technology
Publications - 8
Citations - 56
Rupali Sandip Kute is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Facial recognition system & Computer science. The author has an hindex of 3, co-authored 5 publications receiving 33 citations. Previous affiliations of Rupali Sandip Kute include College of Engineering, Pune & Maharashtra Institute of Technology.
Papers
More filters
Journal ArticleDOI
Component-based face recognition under transfer learning for forensic applications
TL;DR: A novel approach for component-based face recognition and association under transfer learning is proposed and it is demonstrated that the knowledge gained from complete face images is transferred to classify components of the face.
Journal ArticleDOI
Transfer learning for face recognition using fingerprint biometrics
TL;DR: In this paper, Bregman divergence regularization is used to learn and optimize transferring subspace, which helps to find a common subspace that boosts the performance of independent and identically distributed (i.i.d.) condition of samples.
Journal ArticleDOI
Association of Face and Facial Components Based on CNN and Transfer Subspace Learning for Forensics Applications
TL;DR: For the transfer, the proposed Fisher linear discriminant analysis and locality preserving projection, a convolutional neural network-based algorithm gives 91% and 90% accuracy, respectively, which outperforms the Histogram of Gradient and Gabor methods for predicting an association.
Journal ArticleDOI
Cross domain association using transfer subspace learning
TL;DR: A cross domain association between face and fingerprint that finds utility in forensic applications is proposed and is proposed using Fisher Linear Discriminant Analysis subspace learning algorithm.
Proceedings ArticleDOI
Biometric association using transfer subspace learning
Rupali Sandip Kute,Vibha Vyas +1 more
TL;DR: Two biometrics, face and fingerprint are considered and associated with each other using transfer subspace learning and the proposed framework will be very useful in the forensic applications.