L
Luciana Morogan
Researcher at Military Technical Academy
Publications - 14
Citations - 29
Luciana Morogan is an academic researcher from Military Technical Academy. The author has contributed to research in topics: Deep learning & Encryption. The author has an hindex of 2, co-authored 14 publications receiving 24 citations.
Papers
More filters
Proceedings ArticleDOI
Efficient and robust perceptual hashing using log-polar image representation
Cezar Plesca,Luciana Morogan +1 more
TL;DR: A novel algorithm for generating an image hash based on Log-Polar transform features, which is a part of the Fourier-Mellin transformation, often used in image recognition and registration techniques due to its invariant properties to geometric operations.
Proceedings ArticleDOI
RoWordNet – A Python API for the Romanian WordNet
TL;DR: A new library (API) that provides easy access to the Romanian WordNet and an application based on the API to perform embedded vector retrofitting, using the synonymy/antonymy relations extracted from RoWnt to tune the word vectors under these semantic constraints, effectively specializing the vector space.
Proceedings Article
LiRo: Benchmark and leaderboard for Romanian language tasks
Stefan Daniel Dumitrescu,Petru Rebeja,Beata Lorincz,Mihaela Gaman,Andrei Avram,Mihai Ilie,Andrei Pruteanu,Adriana Stan,Lorena Rosia,Cristina Iacobescu,Luciana Morogan,George Dima,Gabriel Marchidan,Traian Rebedea,Madalina Chitez,Dani Yogatama,Sebastian Ruder,Radu Tudor Ionescu,Razvan Pascanu,Viorica Patraucean +19 more
Book ChapterDOI
View from Inside One Neuron
TL;DR: The process of learning at ”molecular” level (internal neural learning) under the form of a computational algorithm inspired by a real brain functioning, has been introduced.
Comparison-based applications for fully homomorphic encrypted data
TL;DR: This article presents a practical application of the homomorphic encryption schemes, namely the problem of finding maximum/minimum from a collection of encrypted integers, and presents an algorithm that can be run directly in cloud without the need for an intermediate data exchange with the client.