Petra Bosilj

Learn More
This article presents a technique that arranges the elements of hierarchical representations of images according to a coarseness attribute. The choice of the attribute can be made according to prior knowledge about the content of the images and the intended application. The transformation is similar to filtering a hierarchy with a non-increasing attribute,(More)
The rapidly increasing volume of visual Earth Observation data calls for effective content based image retrieval solutions, specifically tailored for their high spatial resolution and heterogeneous content. In this paper, we address this issue with a novel local implementation of the well-known morphological descriptors called pattern spectra. They are(More)
We propose a local region descriptor based on connected pattern spectra, and combined with normalized central moments. The descriptors are calculated for MSER regions of the image, and their performance compared against SIFT. The MSER regions were chosen because they can be efficiently selected by constructing a max-tree, a structure used to calculate both(More)
Detection of local features which are distinctive, invariant and discriminative is used to construct compact image representations in many computer vision applications. Achieving robustness against viewpoint change motivated the development of affine invariant detectors responding to image gradient or contrast changes, edges or corners. We focus on the(More)
I would like to thank my supervisor Siniša Šegvic for all the patience and support he offered during my studies, and especially while I was writing this thesis. He was always happy to help and share his knowledge with his students, and I am very glad I was able to learn from him. Seeing his unwavering inspiration has inspired me to pursue a research career.(More)