Affiliations: Department of Mathematics; Department of Computer
Science, Texas A&D University, Commerce, TX, USA | Department of Computer Science, Texas A&D University,
Commerce, TX, USA | College of Humanities, Social Sciences and Arts, Texas
A&D University, Commerce, TX, USA
Abstract: The present work is a part of research study aiming to develop an
algorithm and a software system capable of quick identification of weapons and
relations between human and a weapon in a scene. Bridging the semantic gap
between the low level knowledge extracted from an image and the high level
semantics needed to negotiate the weapon domain ontology is connected to the
features extraction algorithms. Also, the ontology is anticipated to help
facilitate the recognition part of the work. To accelerate the search process a
hierarchy of attributes and concepts will be applied to cluster the ontology
using a set of extracted features. The ontological structure, the clustering
ideas and the feature extraction approaches and algorithms are introduced in
the paper. Experimental results for boundary and convex hull extraction are
shown as well. The paper ends with discussion and the future directions of the present work.
Keywords: features extraction, hierarchy of attributes, semantics, clustering, ontology, weapons
