J.-M. Ogier, W. Liu, and J. Lladós (Eds.): GREC 2009, LNCS 6020, pp. 231–241, 2010. © Springer-Verlag Berlin Heidelberg 2010 Segmentation of Colour Layers in Historical Maps Based on Hierarchical Colour Sampling Stefan Leyk Department of Geography, University of Colorado, 260 UCB, Boulder, CO 80309, USA stefan.leyk@colorado.edu Abstract. A colour image segmentation (CIS) process for scanned historical maps is presented to overcome common problems associated with segmentation of old documents such as (1) variation in colour values of the same colour layer within one map page, (2) differences in typical colour values between homoge- neous areas and thin line-work, which belong both to the same colour layer, and (3) extensive parameterization that results in a lack of robustness. The described approach is based on a two-stage colour layer prototype search using a con- strained sampling design. Global colour layer prototypes for the identification of homogeneous regions are derived based on colour similarity to the most ex- treme colour layer values identified in the map page. These global colour layer prototypes are continuously adjusted using relative distances between prototype positions in colour space until a reliable sample is collected. Based on this sam- ple colour layer seeds and directly connected neighbors of the same colour layer are determined resulting in the extraction of homogeneous colour layer regions. In the next step the global colour layer prototypes are recomputed using a new sample of colour values along the margins of identified homogeneous coloured regions. This sampling step derives representative prototypes of map layer sec- tions that deviate significantly from homogeneous regions of the same layers due to bleaching, mixed or false colouring and ageing of the original scanned documents. A spatial expansion process uses these adjusted prototypes as start criterion to assign the remaining colour layer parts. The approach shows high robustness for map documents that suffer from low graphical quality indicating some potential for general applicability due to its simplicity and the limited need for preliminary information. The only input required is the colours and number of colour layers present in the map. Keywords: Colour image segmentation, two-stage colour sampling, historical maps, homogeneity, cartographic pattern recognition. 1 Introduction The unique value of cartographic documents for the extraction of spatial information about the landscape has motivated a number of research efforts including the recogni- tion of e.g., elevation contours [1], roads [2], symbol chains [3], forest area [4], or map text [5]. Topographic maps show the highest degree of complexity [6,7] and,