Title :
Recognition of partially occulted objects
Author :
Aoudia, Amina Ait ; Aouat, Saliha
Author_Institution :
Comput. Sci. Dept., Univ. of Sci. & Technol. - Houari, Boumediene, Algeria
Abstract :
We propose a new method to recognize partially occulted objects. The technique consists to create first, an index containing codes associated to each image of the database using the Quad-tree structure, and then we define a tolerance threshold that allows the recognition of partially occulted objects.
Keywords :
computer graphics; object recognition; quadtrees; partially occulted object recognition; quad-tree structure; tolerance threshold; Computer science; Data structures; Educational institutions; Image recognition; Indexes; Object recognition; Index; Occlusion; Quad-tree; Silhouette;
Conference_Titel :
Computer Systems and Applications (AICCSA), 2013 ACS International Conference on
Conference_Location :
Ifrane
DOI :
10.1109/AICCSA.2013.6616484
