S
Selim Aksoy
Researcher at Bilkent University
Publications - 107
Citations - 3097
Selim Aksoy is an academic researcher from Bilkent University. The author has contributed to research in topics: Image segmentation & Feature extraction. The author has an hindex of 27, co-authored 103 publications receiving 2755 citations. Previous affiliations of Selim Aksoy include University of Washington.
Papers
More filters
Journal ArticleDOI
Feature normalization and likelihood-based similarity measures for image retrieval
Selim Aksoy,Robert M. Haralick +1 more
TL;DR: The effects of five feature normalization methods on retrieval performance are discussed and two likelihood ratio-based similarity measures that perform significantly better than the commonly used geometric approaches like the Lp metrics are described.
Journal ArticleDOI
Automatic Detection of Geospatial Objects Using Multiple Hierarchical Segmentations
H.G. Akcay,Selim Aksoy +1 more
TL;DR: Novel methods for automatic object detection in high-resolution images by combining spectral information with structural information exploited by using image segmentation are presented.
Journal ArticleDOI
Unsupervised segmentation and classification of cervical cell images
TL;DR: An unsupervised approach for the segmentation and classification of cervical cells and performance evaluation using two data sets show the effectiveness of the proposed approach in images having inconsistent staining, poor contrast, and overlapping cells.
Journal ArticleDOI
Learning bayesian classifiers for scene classification with a visual grammar
TL;DR: A Bayesian framework for a visual grammar that aims to reduce the gap between low-level features and high-level user semantics is described and experiments show that the visual grammar enables creation of high- level classes that cannot be modeled by individual pixels or regions.
Journal ArticleDOI
Detection and classification of cancer in whole slide breast histopathology images using deep convolutional networks.
TL;DR: A system that classifies whole slide images of breast biopsies into five diagnostic categories, including atypical ductal hyperplasia, ductal carcinoma in situ, and invasive carcinoma, is presented.