Vesna Zeljkovic
Lincoln University (Pennsylvania)
78 Papers
166 Citations
Vesna Zeljkovic is an academic researcher from Lincoln University (Pennsylvania). The author has contributed to research in topics: Object detection & Image segmentation. The author has an hindex of 8, co-authored 75 publications. Previous affiliations of Vesna Zeljkovic include New York Institute of Technology & Prince Mohammad bin Fahd University.
Chat about Author
Papers
Automatic algorithm for inverse synthetic aperture radar images recognition and classification
TL;DR: An algorithm for automatic aircraft categories that is models classification from inverse synthetic aperture radar (ISAR) images that use pulse reflection shape and Doppler shifts of parts of aircraft that are in any maneuver that introduces rotation to the target is proposed.
31
Supplemental melanoma diagnosis for darker skin complexion gradients
Vesna Zeljkovic,Christopher Druzgalski,S. Bojic-Minic,Claude Tameze,P. Mayorga +4 more
- 23 Mar 2015
TL;DR: Computer assisted diagnostic tool for melanoma detection focused on dark and fair complexion skin which adds more objective judgments based on quantitative measures was developed and tested utilizing databases including images of a variety of skin cancer manifestations.
30
Automatic brain tumor detection and segmentation in MR images
Vesna Zeljkovic,Christopher Druzgalski,Y. Zhang,Z. Zhu,Z. Xu,D. Zhang,P. Mayorga +6 more
- 07 Apr 2014
TL;DR: An automated algorithm for brain tumor detection and medical doctors' assistance in facilitated and accelerated diagnosis procedure has been developed and initially tested on images obtained from the patients with diagnosed tumors and healthy subjects.
28
Classification algorithm of retina images of diabetic patients based on exudates detection
Vesna Zeljkovic,Milena Bojic,Claude Tameze,Ventzeslav Valev +3 more
- 02 Jul 2012
TL;DR: An automated algorithm is proposed that applies mathematical modeling which enables light intensity levels emphasis, easier exudates detection, efficient and correct classification of retina images, and is robust to various appearance changes of retinal fundus images which are usually processed in clinical environments.
20
Quartiles and Mel Frequency Cepstral Coefficients vectors in Hidden Markov-Gaussian Mixture Models classification of merged heart sounds and lung sounds signals
P. Mayorga,Daniela Ibarra,Vesna Zeljkovic,Christopher Druzgalski +3 more
- 20 Jul 2015
TL;DR: An assessment of the number of clusters using dendrograms, silhouettes, and BIC linked with the models' size allows to enhance efficiency of merged HMM-GMM models in diagnostic classification of cardiopulmonary acoustic signals.
13