Artificial Neural Network for Displacement Vectors Determination

Abstract

An artificial neural network (NN) for displacement vectors (DV) determination is presented in this paper. DV are computed in areas which are essential for image analysis and computer vision, in areas where are edges, lines, corners etc. These special features are found by edges operators with the following filtration. The filtration is performed by a threshold function. The next step is DV computation by 2D Hamming artificial neural network. A method of DV computation is based on the full search block matching algorithms. The pre-processing (edges finding) is the reason why the correlation function is very simple, the process of DV determination needs less computation and the structure of the NN is simpler.