Abstract: A system and method for identifying and locating instances of a shape under large variations in linear degrees of freedom is provided. The invention extracts boundary segments from an image and generates potential match candidates for boundary models based on the extracted boundary segments. The invention also extracts skeletal segments from the obtained image. Potential match candidates are then generated for skeletal models based on the extracted skeletal segments. Once the match candidates for the boundary models and skeletal models have been generated, the present invention then corresponds the various boundary segments and outputs a best correspondence. The output from the present invention may be utilized by a user to signify acceptance of the various correspondences located by the present invention. These correspondences may then be utilized to train a machine vision system.

Abstract: Determining the position of a generally rectangular device is achieved by performing subsampling of image data, thresholding of the subsampled data, extraction of boundary features based on the output of the thresholding, calculation of correspondence between extracted boundary features and the generally rectangular device, and a final fit against a model of the generally rectangular device. Correspondence between the boundary features of the image and the generally rectangular device is performed by locating points in the extracted boundary feature which may correspond to corners of the generally rectangular device, removing those points which correspond to known objects other than the generally rectangular device, removing those points likely to belong to unknown objects, and fitting the points to an input model of the generally rectangular device to determine its position.