Automatic Extraction of Forests from Historical Maps Based on Unsupervised Classification in the CIELab Color Space

In this chapter, we describe an automatic procedure to capture features on old maps. Early maps contain specific informations which allow us to reconstruct trajectories over time and space for land use/cover studies or urban area development. The most commonly used approach to extract these elements requires a user intervention for digitizing which widely limits its utilization. Therefore, it is essential to propose automatic methods in order to establish reproducible procedures. Capturing features automatically on scanned paper maps is a major challenge in GIS for many reasons: (1) many planimetric elements can be overlapped, (2) scanning procedure may conduct to a poor image quality, (3) lack of colors complicates the distinction of the elements. Based on a state of art, we propose a method based on color image segmentation and unsupervised classification (K-means algorithm) to extract forest features on the historical ‘Map of France’. The first part of the procedure conducts to clean maps and eliminate elevation contour lines with filtering techniques. Then, we perform a color space conversion from RGB to L*a*b color space to improve uniformity of the image. To finish, a post processing step based on morphological operators and contextual rules is applied to clean-up features. Results show a high global accuracy of the proposed scheme for different excerpt of this historical map.

[1]  M. Bürgi,et al.  Reconstructing the collapse of wetland networks in the Swiss lowlands 1850–2000 , 2011, Landscape Ecology.

[2]  Chew Lim Tan,et al.  Text/Graphics Separation in Maps , 2001, GREC.

[3]  Paul F. Whelan,et al.  Colour Image Analysis , 2001 .

[4]  D. Narmadha,et al.  A Survey on Image Denoising Techniques , 2012 .

[6]  Paolo Gamba,et al.  Perceptual grouping for symbol chain tracking in digitized topographic maps , 1999, Pattern Recognit. Lett..

[7]  Kuo-Chin Fan,et al.  Automatic data capture for geographic information systems , 1999, IEEE Trans. Syst. Man Cybern. Part C.

[8]  Robert G. Cromley,et al.  Measuring Historical Coastal Change using GIS and the Change Polygon Approach , 2012, Trans. GIS.

[9]  Jacek Kozak,et al.  Automatic detection of forest regions on scanned old maps , 2012 .

[10]  Robert Mariani,et al.  Topographic Maps Automatic Interpretation: Some Proposed Strategies , 1997, GREC.

[11]  Marc M. Ansoult,et al.  Mathematical Morphology : A Tool for Automated GIs Data ~ cquisition from Scanned Thematic Maps , 2007 .

[12]  Craig A. Knoblock,et al.  Efficient and Robust Graphics Recognition from Historical Maps , 2011, GREC.

[13]  Rangachar Kasturi,et al.  Interpretation of telephone system manhole drawings , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[14]  Toru Kaneko.  Line structure extraction from line-drawing images , 1992, Pattern Recognit..

[15]  S. Cousins,et al.  Analysis of land-cover transitions based on 17th and 18th century cadastral maps and aerial photographs , 2004, Landscape Ecology.

[16]  P Ganesan,et al.  Segmentation and edge detection of color images using CIELAB color space and edge detectors , 2010, INTERACT-2010.

[17]  Jorge Silva Centeno.  Segmentation of Thematic Maps Using Colour and Spatial Attributes , 1997, GREC.

[18]  Thomas C. Henderson,et al.  Automatic Segmentation of Semantic Classes in Raster Map Images , .

[19]  Luyang Li,et al.  Cooperative text and line-art extraction from a topographic map , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[20]  William R. Mathew,et al.  Color as a Science , 2005 .

[21]  Zheru Chi,et al.  Map image segmentation based on thresholding and fuzzy rules , 1993 .

[22]  Prasanna G. Mulgaonkar,et al.  Verification-Based Approach for Automated Text and Feature Extraction from Raster-Scanned Maps , 1995, GREC.

[23]  Pierre Soille,et al.  From scanned topographic maps to digital elevation models by , 2001 .

[24]  Anna Bentkowska-Kafel,et al.  Computer Vision and Image Analysis of Art II , 2010 .

[25]  Oliver Bender,et al.  Using GIS to analyse long-term cultural landscape change in Southern Germany , 2005 .

[26]  David A. Butler,et al.  An evaluation of color spaces fordetecting defects in Douglas-fir veneer , 1992 .

[27]  Manfred F. Buchroithner,et al.  Field-based landcover classification using TerraSAR-X texture analysis , 2011 .

[28]  Stephen Wise.  Extracting raster GIS data from scanned thematic maps , 1999, Trans. GIS.

[29]  Hanan Samet,et al.  MAGELLAN: Map Acquisition of GEographic Labels by Legend ANalysis , 1998, International Journal on Document Analysis and Recognition.

[30]  J. Serra,et al.  MATHEMATICAL MORPHOLOGY IN COLOR SPACES APPLIED TO THE ANALYSIS OF CARTOGRAPHIC IMAGES , 2003 .

[31]  Yves Lecourtier,et al.  5 - Interprétation de cartes géographiques : Algorithmes de reconstruction des réseaux hydrographiques et routiers , 1997 .

[32]  Robert Weibel,et al.  Saliency and semantic processing: Extracting forest cover from historical topographic maps , 2006, Pattern Recognit..

[33]  Peter Bajcsy,et al.  Automation of digital historical map analyses , 2011, Electronic Imaging.

[34]  Allan Hanbury,et al.  Colour Image Analysis in 3D-Polar Coordinates , 2003, DAGM-Symposium.

[35]  Refik Samet,et al.  AN IMPLEMENTATION OF AUTOMATIC CONTOUR LINE EXTRACTION FROM SCANNED DIGITAL TOPOGRAPHIC MAPS , 2010 .

[36]  S. Mitra,et al.  Unsupervised segmentation of color images based on k-means clustering in the chromaticity plane , 1999, Proceedings IEEE Workshop on Content-Based Access of Image and Video Libraries (CBAIVL'99).