Hosticka, B.J.B.J.HostickaMöschen, J.J.Möschen2022-03-082022-03-081990https://publica.fraunhofer.de/handle/publica/317866In this paper a statistical approach for pattern recognition, based on a distance transformation, will be presented. The algorithm enables multiclass rotation- and translation invariant pattern recognition and can be made optionally scale invariant. Beside the theory of the algorithm we will present some practical application examples and propose a system architecture for a high speed hardware implementation including an ASIC architecture.endistance transformationHistogram classificationMustererkennungRotation-invarianceScaling-invariance621conference paper