S
Sos S. Agaian
Researcher at City University of New York
Publications - 582
Citations - 10193
Sos S. Agaian is an academic researcher from City University of New York. The author has contributed to research in topics: Image processing & Computer science. The author has an hindex of 38, co-authored 532 publications receiving 8216 citations. Previous affiliations of Sos S. Agaian include College of Staten Island & University of Texas System.
Papers
More filters
Proceedings ArticleDOI
Thermal Image Enhancement Algorithm Using Local And Global Logarithmic Transform Histogram Matching With Spatial Equalization
TL;DR: A new thermal image enhancement algorithm based on combined local and global image processing in the frequency domain using logarithmic transform histogram matching with spatial equalization approach on different image blocks to produce a weighted mean of all processing blocks.
Proceedings ArticleDOI
Mammogram enhancement using alpha weighted quadratic filter
TL;DR: A new powerful nonlinear filter called the alpha weighted quadratic filter for mammogram enhancement that can be used for automatic segmentation and excellent enhancement results can be obtained with no apriori knowledge of the mammogram contents.
Journal ArticleDOI
New look on quantum representation of images: Fourier transform representation
TL;DR: A new approach for representing discrete signals and images in quantum computing, by mapping the input data into the unit circle, or only part of the circle, is proposed, allowing for introducing the concept of the Fourier transform qubit representation.
Journal ArticleDOI
TMO-Net: A Parameter-Free Tone Mapping Operator Using Generative Adversarial Network, and Performance Benchmarking on Large Scale HDR Dataset
TL;DR: In this article, a large scale HDR image benchmark dataset (LVZ-HDR dataset) is created to enable performance evaluation of TMOs across a diverse conditions and scenes that will also contribute to facilitate the development of more robust TMO operators using state-of-the-art deep learning methods.
Proceedings ArticleDOI
Fingerprint authentication using geometric features
TL;DR: A versatile local feature fingerprint matching scheme that improves the accuracy of the fingerprint authentication system, works when the minutiae information is sparse, and produces satisfactory matching accuracy in the case when minutia information is unavailable.