N
Nathan S. Netanyahu
Researcher at Bar-Ilan University
Publications - 150
Citations - 12080
Nathan S. Netanyahu is an academic researcher from Bar-Ilan University. The author has contributed to research in topics: Image registration & Deep learning. The author has an hindex of 27, co-authored 144 publications receiving 11131 citations. Previous affiliations of Nathan S. Netanyahu include Universities Space Research Association & University of Maryland, College Park.
Papers
More filters
Book ChapterDOI
Handwriting-Based Gender Classification Using End-to-End Deep Neural Networks
TL;DR: This paper proposed a novel deep learning-based approach for handwriting-based gender classification, which performs automatic feature extraction from a given handwritten image, followed by classification of the writer's gender.
Journal ArticleDOI
Mean shift-based clustering of remotely sensed data with agricultural and land-cover applications
TL;DR: The mean shift algorithm is revisited and the classification accuracy of remotely sensed images as a function of various MS parameters, such as the variant used, kernel type, dimensionality, kernel bandwidth, etc, is investigated.
Journal ArticleDOI
Approximating large convolutions in digital images
David M. Mount,Tapas Kanungo,Nathan S. Netanyahu,Christine D. Piatko,Ruth Silverman,Angela Y. Wu +5 more
TL;DR: An algorithm for computing binary convolutions of this form, where the kernel of the binary convolution is derived from a convex polygon, based on a novel use of Bresenham's line-drawing algorithm and prefix-sums to update the convolution incrementally as the kernel is moved from one position to another across the image.
Proceedings ArticleDOI
Painter classification using genetic algorithms
TL;DR: This paper provides initial promising results for the 2- and 3-class cases, which offer significant improvement in comparison to a standard nearest neighbor classifier.
Book ChapterDOI
Image Registration for Remote Sensing: New approaches to robust, point-based image registration
TL;DR: Experimental studies show that the new distance measure considered can provide significant improvements over the partial Hausdorff distance in instances where the number of outliers is not known in advance, and shows that the other algorithmic improvements can offer tangible improvements.