Analysis of metrics to determine similarity between restrict non-rigid objects in real time.
Similarity metric, non-rigid objects, restricted deformation, point clouds, Mahalanobis distance, Hausdorff distance, real time
Within the area of Mechatronics, mainly in CAD and computer vision, many applications are developed that involve the analysis of non-rigid or deformable objects.This master dissertation proposes an approach to measure similarity of deformable objects using as underlying representation clouds of three dimensional points of them. Basically, three point clouds of the analyzed object are considered: one without changes, another representing the degree of maximum deformation and a third that describes the deformation of interest. Here are presented two alternatives to measure similarity based on Distance measures, with the respective accuracy and time checks. The first method is based on the Mahalanobis distance computation and in the second the Hausdorff distance is used with a previous registration and alignment steps. The experiments are developed considering some parts of the human body, its evidents that the analysis with Mahalanobis distance has the shortest execution time. Several applications in the areas initially mentioned and in others as Virtual Reality can rely on the results obtained in this proposal to determine the deformation levels of restricted deformable objects.