AUTOMATIC OBJECT IDENTIFICATION USING VISUAL LOW LEVEL FEATURE EXTRACTION AND ONTOLOGICAL KNOWLEDGE

  • Authors:
  • Nikolay Metodiev Sirakov;Sang C. Suh;Salvatore Attardo

  • 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

  • Venue:
  • Journal of Integrated Design & Process Science
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

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.