A Semi-Automatic Spatial Feature Extraction Tool for Minimising Errors in GIS Data Capture

Saviour Mantey


In GIS projects, data capture and maintenance are both capital and labour intensive. Over the past few years, vector data for GIS analysis have been extracted by hours of tedious and manual digitising. This method of digitising is subjective and prone to human errors. The credibility of a GIS analysis is strongly influenced by the quality of data used. The objective of this study was therefore to minimise the errors in GIS vector data capture from raster models. This was achieved by developing a semi-automatic spatial feature extraction tool. The tool is capable of extracting spatial features from orthophotos, scanned maps and high resolution satellite images. The procedures employed include; image classification, edge detection and segmentation of images as well as extraction of spatial features from raster images. Finally, the extracted features were converted to vector or GIS compatible formats such as ESRI shapefiles and other CAD formats. The result is an application capable of creating a ready-to-use vector maps by extracting spatial features from raster models within the shortest possible time. This tool is also useful for map revision and converting hard-copy maps to digital formats. 



Raster Data, Vector Data, Semi-Automatic Spatial Feature, ESRI Shapefiles

Full Text:



Burroughs, P.A. (1986), Principles of Geographical Information Systems for Land Resources Assessment. Clarendon Press, Oxford, pp.193.

David, J. B. (2013a), “GIS Data Types”, Bio Diversity GIS, www.bgis.sanbi.org/gis-primer/page_14.htm. [Accessed: March 14, 2017].

David, J. B. (2013b), “Vector Data Formats”, Bio Diversity GIS, www.bgis.sanbi.org/gis-primer/ page_16.htm. [Accessed: December 14, 2017].

Dempsey, C. (2006), “Methods for Creating Spatial Databases”, GIS Lounge. www.gislounge.com/methods-for-creating-spatial-databases/. [Accessed: January 20, 2018].

Dempsey, C. (2012), “Digitising Errors in GIS”, GISLounge,www.gislounge.com/digitizing-errors-in-gis/.[Accessed: January 20, 2018].

Douglas, D. H. and Peucker, T. K. (1973), "Algorithms for the reduction of the number of points required to represent a digitized line or its caricature". Canadian Cartographer, 10: 1 pp. 12- 122.

Feng, Y (2003), Combined Galileo and GPS: A Technical Perspective. Journal of Global Positioning Systems, 2 (1): pp. 67-72.

Jenks, G. F. (1981), "Lines, Computers, and Human Frailties". American Association of Anthropological Genetics, 7 l (1): pp. 1 – 10.

Kang-tsung, Chang, (2006), “Introduction to Geographic Information Systems”, Third Edition, McGraw-Hill, pp.506.

Lachapelle, G. M.E., Cannon, K. O’Keefe, and P. Alves (2002), How Will Galileo Improve Positioning Performance? GPS World, 13 (9): pp. 38 – 48.

Manuel, S. Pascual. (2011), “GIS Data: A Look at Accuracy, Precision and Types of Errors”, GIS Lounge, www.gislounge.com/methods-for-creating-spatial-databases/. [Accessed: January 2, 2018].

Mulassano P., Dovis F., cllomb F. (2004), European projects for innovative GNSS-related applications. GPS Solutions, 7: pp. 268-270.

Oddei, G. (2011), “Image Classification Using Matlab” Unpublished BSc Project, University of Mines and Technology, Tarkwa, pp. 16-24.

Salgado, S, Abbondanza, S, Blondel, R and Lannelongue, S (2001), Constellation availability concepts for Galileo, Proceedings of Institute of Navigation, Long Beach, CA, 22-24 January 2001, pp. 778-786.

Yecheng, T. Wu. (1999), “Raster, Vector and Automated Map Digitising”, www.ablesw.com/r2v/rasvect.html. [Accessed: January 21, 2018].


  • There are currently no refbacks.