Method For Recognition of Ocluded Objects

Alejandro Pacheco Morales, Fidel Guerrero Peña, Alejandro Garcés Calvelo, Luis A. Rodríguez Reiners

Abstract


This paper proposes a method to recognizeoccluded objects in digital images. It provides a new approach to the use of Hidden Markov Models for segmentation of overlapping objects. To validate the proposed method several experiments were executed with different databases. In all cases high levels of effectiveness were obtained.

Keywords


Digital images, occlusion, Hidden Markov Models, segmentation.

Full Text: PDF (Spanish)