Abstract:
Shape description is a crucial step in many computer vision applications. This thesis is an attempt to introduce various representations of two and three dimensional shape information. These representations are aimed to be in homogeneous parametric forms in 2D or 3D space, such that subspace-based feature extraction techniques are applicable on them. We tackle three di erent applications: (i) Person recognition with hand biometry, (ii) Person recognition with three-dimensional face biometry, (iii) Indexing and retrieval of generic three-dimensional models. For each application, we propose various combinations of shape representation schemes and subspace-based feature extraction methods. We consider subspaces with fixed bases such as cosines, complex exponentials and tailored subspaces such as Principal Component Analysis, Independent Component Analysis and Nonnegative Matrix Factorization. Most of the descriptors we propose are dependent on the pose of the object. In this thesis we give special emphasis on the pose normalization of objects. This challenging step is highly application-specific. For hands and 3D faces, anatomical landmarks are used in order to reduce within-class variations due to pose, expression and articulation, whereas generic 3D models lack common landmarks. In order to deal with this disadvantage of generic models, we propose solutions that operate both in the pre-processing stage and in the matching stage.
