MORSE: An Architecture for 3D Object Recognition Based on Invariants

Over the past few years, there has been considerable interest in the application of geometric invariance to the problem of object recognition[2, 3, 4, 5, 6]. While most work has focused on the problem of discovering and characterizing new geometric invariants, several recognition systems, based on invariants have been implemented. A key example is the LEWIS[7] system. LEWIS exploits projective invariants of planar objects to enable object indexing and classification. Experience with LEWIS and its limitations, motivated the MORSE 6 The MORSE project, started in January 1994, has the goal of providing a Cq-+ environment for the implementation of a system for recognizing 3D objects based on invariant class descriptions. MORSE embodies invariant representations for geometric classes of 3D objects such as: rotational symmetry, translational symmetry and polyhedra. The architecture is designed to support image segmentation, classbased grouping, model library management and scene reasoning. The LEWIS system has also been re-implemented using the MORSE infrastructure to provide for recognition of planar objects. To motivate the architectural design, it will prove useful to review and contrust the key steps in object recognition for two geometric classes: rotational symmetry and structures repeated by translation. Then we will describe how these steps are mapped onto the implemented architecture. Both classes require the segmentation of image features from regions of interest. In MORSE, edgel segmentation is carried out using a modified Canny edge detector and connected edgel chains are linked topologically to form a connected network of boundary segments. The two classes have different feature grouping stages, as follows.