Affine curvature scale space with affine length parametrisation

The maxima of Curvature Scale Space (CSS) image have been used to represent 2D shapes under affine transforms. The CSS image is expected to be in the MPEG-7 package of standards, Since th CSS image employs the are length para metrisation which is not affine invariant, we expect some deviations in the maxima of the CSS image under general affine transforms. Affine length and affine curvature have already been introduced and used as alternatives to are length and conventional curvature in affine transformed environments. T he utility of using these parameters to enrich the CSS representation is ad dressed in this payer. We use are length to parametrise the curve Frier to computing its CSS image. The parametrisation has been proven to be invarian t under affine transformation and has been used in many affine invariant sh ape recognition methods. Since the organisation of the CSS image is based o n curvature zero crossings oi the curve, in this paper, we also investigate the advantages and shortcomings of using affine curvature in computation o f the CSS image. The enriched CSS representations are then used to find sim ilar shapes from a very Large prototype database, and also a small classifi ed database, both consisting of original as well as affine transformed shap es. An improvement is observed over the conventional CSS image.