Robust normalization of silhouettes for ecognition applications

摘要

In this work we introduce a new silhouette normalization method, which is robust with respect to deformations and enables the use of image domain based similarity measures for recognition applications. It is shown that a template matching operation can provide an accurate shortlist of candidates suitable for a more exact matching engine in spite of projective transformations and silhouette deformations. This retrieval of similar shapes has a low computational cost and has been tested with silhouettes of natural and man-made objects.