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

Abstract

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.

Historical ponds of the Czech Republic: an example of the interpretation of historic maps

“…Personally, we had to deal with issues connected with interpretations of map content -water areas in individual map sheet of the 2nd Military Survey whose colourisation and original hues were altered to a degree due to light conditions. This fact made it virtually impossible to apply the potential methods of automatic classification (Herrault, Sheeren, Fauvel, & Paegelow, 2013). Each water area thus had to be identified individually.…”

An Adaptable Approach for Generating Vector Features from Scanned Historical Thematic Maps Using Image Enhancement and Remote Sensing Techniques in a Geographic Information System

“…Even further, Chiang, Leyk, and Knoblock (2013) investigated graphics recognition techniques that required interactive user participation, while Baily et al (2011), Dhar, Bikash, andChanda (2006), and Oka, Garg, and Varghese (2012) detailed automatic vectorization of features from maps using varying techniques and methodologies. One of the most recent approaches to solving the raster-to-vector conversion problem came when Herrault et al (2013) utilized an unsupervised classification approach to achieve automatic extraction of forests from historical maps. Unsupervised classifications place pixels into natural groups based on the similarity of the color information of the image (Campbell 1996).…”

Automatic Text Removal and Replacement in Scanned Meteorological Thematic Maps

“…Myers et al (1996) proposed a character recognition based method that uses a verification-based approach to detect text without requiring pre-segmentation graphical entities. Herrault et al (2013) developed an automatic procedure to capture features in old maps. The three-step procedure uses unsupervised classification (K-means algorithm) and color image segmentation to extract forest structures from French historical maps.…”