Algorithm Development for Analysis of Statistical Accuracy of the Extraction of Cartographic Features in Digital Images

Cartography uses large-scale digital images obtained by remote sensing. Such images are commonly used for the extraction and / or detection of cartographic features, which are the targets of interest in mapping. Extracting targets of interest from digital images streamlines the mapping, but the accuracy of this mapping depends on the characteristics of the features of interest present in the extracted image. Therefore, this paper proposes an automated way to calculate and display statistical values so that the extraction processes of any feature type mapping can be assessed considering its quality and quantity. With this purpose in mind, a computer program has been developed. This program applies an already established methodology to calculate statistical values concerning the results obtained by the automatic extraction process. The implemented program performs calculations in a quick and objective manner. In addition, it also generates resultant images that provide the user viewing of the errors obtained by the reported method. This paper presents the results obtained from the use of this computer program. Thus, the program developed accomplishes the proposed objectives, allowing the user to perform a consistent analysis of the automated extraction, since this evaluation is performed based on statistical calculations. Therefore, this program assists researchers and scholars of cartography to evaluate automatic extraction processes in the cartographic features of interest