Summary: Unsupervised Clustering in Hough Space for
Identification of Partially Occluded Objects
Oscar Ya┬n─ez-Sua┬rez, Member, IEEE, and
Mahmood R. Azimi-Sadjadi, Senior Member,
AbstractđAn automated approach for template-free identification of partially
occluded objects is presented. The contour of each relevant object in the analyzed
scene is modeled with an approximating polygon whose edges are then projected
into the Hough space. A structurally adaptive self-organizing map neural network
generates clusters of collinear and/or parallel edges, which are used as the basis
for identifying the partially occluded objects within each polygonal approximation.
Results on a number of cases under different conditions are provided.
Index TermsđImage analysis, occluded objects, unsupervised clustering SOM
network, Hough space.
THE demand of automated procedures for the analysis of digital
scenes has gone beyond the traditional applications of robotic
assembly and production-line inspection. In these applications,
object occlusion probably generates the most significant problem