|
Abstract : |
Abstract. In this article we want to introduce the Gabor wavelet network as a model based approach for an eective and ecient object representation. The Gabor wavelet network has several advantages: invariance to some degree with respect to translation, rotation and dilation, the use of Gabor lters ensured that geometrical and textural object features are encoded, the representation precision ranges from photorealistic to coarse and can be adapted as needed for a specic tast. The feasibility of the Gabor lters as a model for local object features ensures a considerable data reduction while at the same time allowing any desired precision of the object representation ranging from a sparse to a photo-realistic representation. The feasibility of the object representation is veried by a pose estimation experiment. 1, |
