The paper describes the results of an algorithm for determining the position and orientation of an object that lies in front of a monocular camera on a contrasting background. The algorithm is implemented employing the Python language. Many standard image processing operations, such as adaptive threshold segmentation, are used to obtain the edge of the part. In the first step, the edge of the object is selected and its center is determined by calculating the 1st image moment. The orientation of the object is determined using the second moments by calculating the main moments and their axes. The results of applying the algorithm to several different shapes of objects show that the center is determined with sufficient accuracy to capture the object. The accuracy of determining the orientation is sufficient if the principal moments of the image differ significantly from each other.