BDBComp
Parceria:
SBC
Corresponding Geometric Distorted Images using an Uncertainty Inference Method

José Demisio Simões da SilvaPaulo Ouvera Simoni

In this paper we present further results of the application of Dempster-Shafer Theory for uncertainty reasoning in corresponding distorted images in Computer Vision. In previous work Silva and Simoni [12], the model was applied to correspond radiometric distorted images, that is, images presenting differences in brightness and contrast, as an extension of the work developed in Silva and Simoni [11]. The results showed the model is robust when dealing with pairs of non-equalized images and encouraged us to try to correspond geometric distorted images, that is, pairs of images in which one is rotated in relation to the other. In the conducted experiments, the right image was rotated to different angles to simulate the geometric distortions desired. The model corresponded only pair of points in the images and it successfully established the correspondence for the rotated images. As in previous works, the correspondence evidences are based on the contextual and structural features of a point, and they are combined by Dempster´s rule of combination in uncertainty reasoning. A search process maximizes the Belief on the combined evidences.

http://csdl2.computer.org/persagen/DLAbsToc.jsp?resourcePath=/dl/proceedings/&toc=comp/proceedin

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato: bdbcomp@lbd.dcc.ufmg.br
     Mantida por:
LBD