In some cases, images used in satellite data analysis have no accompanying information regarding the sensor model of the satellite and thus, they may require adjustment using other appropriate models. Different methods for the transformation of one coordinate system to another have been proposed,3 e.g., the Helmert transformation, affine transformation, pseudo-affine transformation, projective transformation, second-order conformal transformation, and polynomial transformation. Of these, the polynomial model is simple and easy to use. Historically, polynomial models are among those empirical models used most frequently for fitting functions.4 The distortion is predominantly low frequency and therefore, it can be modeled using a low-order polynomial. Polynomials offer many advantages such as simple form, moderate flexibility of shapes, well-known and understood properties, and ease of use computationally. This model transforms three-dimensional (3-D) object coordinates to image coordinates and converts the data from 3D to two-dimensional (2-D). This transformation requires the use of ground control points (GCPs), which may be obtained using integrated information from ground surveys, photogrammetry, or GPS data comprising , , and coordinates. Rizos and Satirapod5 stated that the differential GPS technique generally provides an accuracy of better than 3 m in the horizontal component at twice the distance root mean square error (RMSE) (at approximately 95% confidence level). The results of the transformation are the coefficients of the polynomial equation.