H
Hasan Sakir Bilge
Researcher at Gazi University
Publications - 81
Citations - 796
Hasan Sakir Bilge is an academic researcher from Gazi University. The author has contributed to research in topics: Facial recognition system & Feature extraction. The author has an hindex of 9, co-authored 72 publications receiving 414 citations. Previous affiliations of Hasan Sakir Bilge include Kırıkkale University & Başkent University.
Papers
More filters
Journal ArticleDOI
Deep Metric Learning: A Survey
Mahmut Kaya,Hasan Sakir Bilge +1 more
TL;DR: This article is considered to be important, as it is the first comprehensive study in which sampling strategy, appropriate distance metric, and the structure of the network are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods.
Journal ArticleDOI
Adaptive multi-element synthetic aperture imaging with motion and phase aberration correction
TL;DR: The results indicate that common spatial frequencies can be used efficiently for correlation processing to correct motion and phase aberration for adaptive multi-element synthetic aperture imaging.
Journal ArticleDOI
Content based image retrieval with sparse representations and local feature descriptors : A comparative study
Ceyhun Celik,Hasan Sakir Bilge +1 more
TL;DR: The most successful approach in the CBIR framework is to use LLC for Coil20 data set and FBSR for Corel1000 data set, and three methods recently proposed in literature (Online Dictionary Learning, Locality-constrained Linear Coding and Feature-based Sparse Representation) are tested and compared with the framework results.
Proceedings ArticleDOI
Recent Trends in Deep Generative Models: a Review
TL;DR: A comprehensive review ofGenerative models with defining relations among them is presented for a better understanding of GANs and AEs by pointing the importance of generative models.
Proceedings ArticleDOI
Motion estimation using common spatial frequencies in synthetic aperture imaging
TL;DR: In this article, the authors explored correlation processing using fully common spatial frequencies of overlapping subapertures for motion estimation between consecutive excitations in multi-element synthetic aperture imaging, and found that signals derived from the subset of elements representing common spatial frequency exhibit significantly higher correlation coefficients than those from signals computed using the entire sub-aperture.