Automatic view selection in multi-view object recognition

We introduce a new method for automatic selection of optimal views in a shape-based method of multi-view 3-D object representation and recognition. A 3-D object is recognised by an optimum number of images taken fr-am different views. The object boundary of each view is consider ed as a 2-D shape and is represented by the locations of the maxima of its Curvature Scale Space (CSS) image contours. An unknown object is then recognised by a single image taken from an arbitrary viewpoint. The method has been tested on a collection of 3-D objects consisting of 15 aircrafts of different shapes. Each abject has been modelled using an optimised number of silhouette contours obtained from different view points. This number varies from 5 to 25 depending on the complexity of the object and the measure of expected accuracy. Around ten silhouette contours corresponding to random views are separately used as input for each object. Results indicated that robust and efficient 3-D free-form object recognition through multi-view representation can be achieved using the CSS representation even for large database retrieval applications.