Abstract
Georeferencing process is one of the most important prerequisites for various geomatics applications; for example, photogrammetry, laser scan analysis, remotely sensing, spatial and descriptive data collection, and others. Georeferencing mostly involves the transformation of coordinates obtained from images that are inhomogeneous due to accuracy differences. The georeferencing depends on image resolution and accuracy level of measurements of reference points ground coordinates. Accordingly, this study discusses the subject of coordinate’s transformation from the image to the global coordinates system (WGS84) to find a suitable method that provides more accurate results. In this study, the Artificial Neural Network (ANN) method was applied, in addition to several numerical methods, namely the Affine divided difference, Newton’s divided difference, and polynomial transformation. The four methods were modelled and coded using Matlab programming language based on an image captured from Google Earth. The image was used to determine reference points within the study area (University of Baghdad campus). The findings of this study showed that the ANN enhanced the results by about 50% in terms of accuracy and 90% in terms of homogeneity, compared with the other methods.
Highlights
The coordinates system is the basis for determining the location or direction of an object in the earth, space or sea, relative to a certain origin, which is the significance of geometrics science [1]
Conclusions several methods for coordinate’s transformation are available, the obtained accuracy level is not the same; it may differ for the same method depending on several factors that include density and distribution of data within the study area, as well as differences in accuracy of data between the two systems
The study discussed the obtained results from an image georeferencing approach based on inconsistent coordinates transformation cases for converting coordinates from the tool to the global coordinates system (WGS84) using four methods, which are the Artificial Neural Network (ANN), Affine divided difference, Newton’s divided difference and the polynomial methods
Summary
The coordinates system is the basis for determining the location or direction of an object in the earth, space or sea, relative to a certain origin, which is the significance of geometrics science [1]. Affine, Helmert, and the projective methods are widely used, which are based on the elements of transformation mathematical models that include scale, rotation, and translation parameters. These traditional methods lack uniform transformation achievements due to insufficient accuracy [6]. The optimization and artificial intelligence methods play an important role in coordinates transformation techniques These methods are based on the estimation of the best solution rather than mathematical models. The results indicated that the ANN method is more accurate and homogeneous for the purpose of the transformation of coordinates from an image system (tool system) to a global system. The polynomial transformation formula can be summarized in Eq 4 and 5 [27]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
