M
Mongi A. Abidi
Researcher at University of Tennessee
Publications - 366
Citations - 7941
Mongi A. Abidi is an academic researcher from University of Tennessee. The author has contributed to research in topics: Image processing & Image segmentation. The author has an hindex of 42, co-authored 365 publications receiving 7573 citations. Previous affiliations of Mongi A. Abidi include Centre national de la recherche scientifique & Oak Ridge National Laboratory.
Papers
More filters
Part decomposition of 3d surfaces
David L. Page,Mongi A. Abidi +1 more
TL;DR: This dissertation describes a general algorithm that automatically decomposes real-world scenes and objects into visual parts using a human vision theory known as the minima rule that states that human visual perception tends to decompose shapes into parts along lines of negative curvature minima.
Proceedings ArticleDOI
Efficient techniques for wide-angle stereo vision using surface projection models
TL;DR: A projection model based on quadric surfaces is presented which accurately characterizes the effect of wide-angle lenses across the entire image and allows for the use of novel feature matching strategies that do not require nonlinear distortion compensation.
Journal ArticleDOI
Contrast-dependent saturation adjustment for outdoor image enhancement
TL;DR: An image enhancement method is proposed, which makes it applicable to enhance outdoor images by using content-adaptive contrast improvement as well as contrast-dependent saturation adjustment, and a simple yet effective prior for adjusting the color saturation depending on the intensity contrast.
Patent
Method of enhancing a digital image by gray-level grouping
TL;DR: An extension of GLG called Selective Gray-Level Grouping (SGLG) is presented in this article, which selectively groups and ungroups histogram components to achieve specific application purposes, such as eliminating background noise, enhancing a specific segment of the histogram and so on.
Journal ArticleDOI
Gaussian fields: a new criterion for 3D rigid registration
TL;DR: A new and simple criterion for rigid registration based on Gaussian fields is introduced, which can extend the size of the region of convergence so that no close initialization is needed, thus overcoming local convergence problems of Iterative Closest Point algorithms.