As large shape repositories become more common, the problem of automatically generating good views of shapes has recently gained prominence. However, very few of the proposed methods take into account the orientation of the shape in the resulting view, and none presents a satisfactory solution. In this paper, we present a simple, example based method to correct the orientation of a shape in a query image. Our method depends on the availability of a database of classified images containing correctly oriented shapes. In the first step, a candidate class for the query shape is identified, and in the second, the query shape is aligned with a target shape from the candidate class.
Waqar Saleem, Danyi Wang, Alexander G. Belyaev, Ha