3-D object recognition using adaptive scale MEGI

We propose a method for recognition of a 3-D object using multi scale description of the object and adaptive matching. MEGI model is a description model to represent arbitrary shapes. However, many MEGI elements are necessary to represent uneven or curved surfaces with accuracy, so it is di cult to use them for recognition. As a solution, we make a tree which corresponds multi scale description of the object. While tracing the tree from the root which corresponds the coarsest representation to leafs, a matching algorithm presented in this paper assigns a di erent scale to each part of the object adaptively and estimates the matching score effectively.