Generic Shape Classification for Retrieval

Abstract

Abstract. We present a shape classification technique for structural content-based retrieval of two-dimensional vector drawings. Our method has two distinguishing features. For one, it relies on explicit hierarchical descriptions of drawing structure by means of spatial relationships and shape characterization. However, unlike other approaches which attempt rigid shape classification, our method relies on estimating the likeness of a given shape to a restricted set of simple forms. It yields for a given shape, a feature vector describing its geometric properties, which is invariant to scale, rotation and translation. This provides the advantage of being able to characterize arbitrary two-dimensional shapes with few restrictions. Moreover, our technique seemingly works well when compared to established methods for two dimensional shapes.

An Approach to the Parameterization of Structure for Fast Categorization

“…The study of Fonseca et al is also a vector-based approach (Fonseca et al, 2006): they describe an entire shape with a single vector, whose dimensions represent trigonometric parameters, such as the area and the perimeter. Their description seems to work well with closed-contour line-drawings, but has not been extended to shapes or structures as obtained from gray-scale images.…”