Abstract: There are disclosed a method and an apparatus for properly recognizing the position and orientation of a whole object article from its partial shape. The method comprises the steps of first extracting an image of a partial shape from a two-dimensional picture image representing at least one portion of the object article whose position and orientation are to be recognized, then calculating at least one of a center of gravity, an intersection of straight lines and a linear equation with respect to each of the extracted feature shapes, thereby obtaining at least one feature parameter, and calculating the position and orientation of the whole object article by arbitrarily combining such feature parameters.

Abstract: A pattern recognition apparatus for recognizing a pattern derived from image data of an outline of an object region is disclosed. The apparatus comprises means for identifying the object region from the input image data, means for extracting outline pixels of the object region, means for polygon-approximating the object region based on a position relationship among the outline pixels to determine vertex coordinates of the approximation polygon, means for determining characteristic data representing a position and an attitude of the region based on the vertex coordinates, and means for superimposing the polygon-approximated object region pattern on a dictionary pattern based on the characteristic data and, determining a common region of the patterns to determine the identity of the patterns. High speed and highly reliable pattern matching is attained.

Abstract: This invention relates to a system which improves an operation speed and accuracy of judgement when the posture of an object component parts is judged by an image processor. This system determines a combination of parameters used for the posture judgement at the time of the preparation of standard data, classifies the types in accordance with the parameter combinations and makes processing for a parameter combination designated for each type at the time of recognition, thereby judging the posture of the object component parts at a high speed and with a high level of accuracy.