A Holistic Workflow for Semi-automated Object Extraction from Large-Scale Historical Maps

Vol.:(0123456789) 1 3 KN - Journal of Cartography and Geographic Information (2023) 73:3–18 https://doi.org/10.1007/s42489-023-00131-z A Holistic Workflow forSemi‑automated Object Extraction fromLarge‑Scale Historical Maps IngaSchlegel1 Received: 23 December 2022 / Accepted: 13 January 2023 / Published online: 10 February 2023 © The Author(s) 2023 Abstract The extraction of objects from large-scale historical maps has been examined in several studies. With the aim to research urban changes over time, semi-automated and transferable holistic approaches remain to be investigated. We apply a combination of object-based image analysis and vectorization methods on three different historical maps. By further matching and georeferencing an appropriate current geodataset, we provide a concept for analyzing and comparing those valuable sources from the past. With minor adjustments, our end-to-end workflow was transferable to other large-scale maps. The findings revealed that the extraction and spatial assignment of objects, such as buildings or roads, enable the comparison of maps from different times and form a basis for further historical analysis. Performing an affine transformation between the datasets, an absolute offset of no more than 72m was achieved. The outcomes of this paper, therefore, facilitate the daily work of urban researchers or historians. However, it should be emphasized that specific knowledge is required for the presented subjective methodology. Keywords Historical maps· Object extraction· Object-based image analysis (OBIA)· Map comparison· Vectorization· Georeferencing Ein holistischer Workflow zur semi-automatisierten Objektextraktion aus großmaßstäbigen historischen Karten Zusammenfassung Die Extraktion von Objekten aus großmaßstäbigen historischen Karten ist Gegenstand zahlreicher Forschungsprojekte. Um den urbanen Wandel im Laufe der Zeit zu untersuchen, bedürfen semi-automatisierte und holistische Ansätze jedoch weiteren Untersuchungen. In dieser Arbeit werden Methoden zur objektbasierten Bildanalyse und Vektorisierung auf drei verschiedene historische Karten angewendet. Mithilfe eines anschließenden Abgleichs sowie der Georeferenzierung eines entsprechenden aktuellen Geodatensatzes stellen wir ein Konzept vor, das sowohl die Analyse als auch den Vergleich der wertvollen Informationsquellen aus der Vergangenheit erlaubt. Nur geringfügige Änderungen waren notwendig, um den ganzheitlichen Arbeitsablauf auf andere großmaßstäbige Karten zu übertragen. Unsere Ergebnisse zeigten, dass die Extraktion und räumliche Zuordnung von Objekten wie Gebäude oder Straßen einen Vergleich zwischen Karten verschiedener Zeitalter ermöglichen und somit eine Grundlage für weitere historische Analysen schaffen. Im Zuge einer affinen Transformation ergab sich eine maximale Abweichung von 72m zwischen beiden Datensätzen. Die Ergebnisse dieser Studie erleichtern damit die tägliche Arbeit von z.B. Stadtforschern oder Historikern. Dennoch sollte berücksichtigt werden, dass die vorgestellte subjektive Methodik spezifisches Fachwissen erfordert. Schlüsselwörter Historische Karten· Objektextraktion· Objektbasierte Bildanalyse (OBIA)· Kartenvergleich· Vektorisierung· Georeferenzierung * Inga Schlegel [email protected] 1 Lab forGeoinformatics andGeovisualization, HafenCity University Hamburg, Henning-Voscherau-Platz 1, 20457Hamburg, Germany 1 Introduction Historical maps are valuable sources when investigating spatial changes over time (Herold 2018). As an essential tool for communicating geographic objects and their locations, they 4 KN - Journal of Cartography and Geographic Information (2023) 73:3–18 1 3 are often the only source of information for the understanding of spatio-temporal change (Sun etal. 2021; Kim etal. 2014). With large-scale maps (approx. > 1:20,000)—especially “city maps”—we are able to study urban morphology (Meinel etal. (2009), as cited in Muhs etal. 2016). Frequently, geographical, political, environmental, and other urbanization processes can be backtraced solely by means of historical maps. For the analysis of the urban landscape of the past, it is inevitable to make the information from large-scale historical maps accessible. Single map objects may provide insights into former names of roads and buildings or their evolution over time. But generally, physical scans (bitmaps) of historical maps are not machine-readable. Manual attempts to acquire information from historical maps are not uncommon but error-prone, time-intensive, and non-transferable (Xydas etal. 2022; Chiang etal. 2020; Gobbi etal. 2019). There is a need for (semi-)automated approaches to solve these problems. In this study, we provide a holistic workflow to not only extract objects from large-scale historical maps, but also to derive benefits from the entirety of geometric, relational, and semantic information. Moreover, our semi-automated approach demonstrates how a spatial assignment between historical and current maps may be enabled and therefore provides a basis for further comparison processes between these. An established strategy used to semi-automatically extract objects from historical maps while minimizing the reader’s subjective influence starts with image segmentation, which follows the principles of human perception: objects within an image are differentiated due to graphical variations (e.g., in light intensity, texture, or spatial context), artifacts, and deviations. Visually homogeneous image areas form so-called segments. By combining object segmentation and classification, the concept of geographic object-based image analysis (GEOBIA) is able to reproduce physically existing objects, like buildings or roads, from raster maps (Herold 2018; Hussain etal. 2013; Hay and Castilla 2008; Neubert 2005). However, authors agree that “there is no single extraction method that can be effectively applied to all different historical maps” (Sun etal. 2021). This is a complex task and only few studies have shown suggestions for further processing and the applicability of their results. Most research in this field aims at extracting and vectorizing geometries from historical maps to make them analyzable, but frequently comes with several limitations and preconditions. Many studies focus on the extraction of a single feature type such as streets (Chiang and Knoblock 2013; Chiang and Knoblock 2012), river bodies (Gede etal. 2020), or different land use classes (Gobbi etal. 2019; Zatelli etal. 2019) like forest areas (Ostafin etal. 2017; Herrault etal. 2013; Leyk etal. 2006) or wetlands (Jiao etal. 2020). Others assume homogeneously colored map regions (Chiang etal. 2011; Leyk and Boesch 2010; Ablameyko etal. 2002), which is rarely true for historical maps. Less complex (“binary”) maps containing homogeneously black objects or contours on white backgrounds were investigated by Xydas etal. (2022), Heitzler and Hurni (2020), Le Riche (2020), Iosifescu etal. (2016), Muhs etal. (2016), and Kim etal. (2014). But differentiating objects solely based on color differences is insufficient especially for widespread monochrome historical maps or due to ancient paper texture, noise, or dirt on the hand-drawn maps (Jiao etal. 2020; Peller 2018; Muhs etal. 2016; Arteaga 2013; Leyk and Boesch 2010). Labels often remain unconsidered in the context of object recognition from historical maps as they commonly suffer from overlaps or gray-scale values similar to textures or contours of other map elements (Heitzler and Hurni 2020; Peller 2018). Other authors presume an existing coordinate system (Le Riche 2020; Gobbi etal. 2019; Iosifescu etal. 2016) or a huge stock of training data, which is needed for machine learning approaches (Xydas etal. 2022; Heitzler and Hurni 2020; Jiao etal. 2020; Gobbi etal. 2019; Zatelli etal. 2019; Uhl etal. 2017). Moreover, few studies have focused on large-scale but rather small-scale maps (Gede etal. 2020; Heitzler and Hurni 2020; Gobbi etal. 2019; Zatelli etal. 2019; Loran etal. 2018; Uhl etal. 2017; Muhs etal. 2016; Herrault etal. 2013). As existing research generally focuses on separate processes involved in object extraction from historical maps, our study suggests a holistic approach composed of extracting, vectorizing, and linking objects. We demonstrate the benefits of eliminating and assigning labels for this whole process and present applicabilities of the resulting geometries. Because only by considering these techniques as a whole, we are able to answer location-related questions on the evolution of geographic features and make historical maps “accessible to geospatial tools and, thus, for spatiotemporal analysis of landscape patterns and their changes” (Uhl etal. 2017). New qualitative and quantitative analyses as well as comparisons to other historical or current geodata become possible by searching through and processing information derived from historical maps (Gobbi etal. 2019; Chiang 2017; Iosifescu etal. 2016). For long-term backtracing of individual buildings, for instance, shape-based comparisons across different maps are useful (Le Riche 2020; Laycock etal. 2011). In this work, we present a semi-automatic solution to make large-scale historical maps usable for spatial analysis while minimizing time-intensive and laborious manual user intervention. Based on our previous findings on the needs of users of historical maps (Schlegel 2019) as well as on the identification and extraction of map labels (Schlegel 2021), we demonstrate the general feasibility of a comprehensive 5KN - Journal of Cartography and Geographic Information (2023) 73:3–18 1 3 workflow composed of (1) eliminating labels, (2) extracting geometries, (3) vectorizing and refining those, and (4) matching and spatially assigning the extracted map objects with current ones. Potential future applications, which are shown in the further course, may be involving semantic information from labels to annotate corresponding map features or an adjustment of a map’s visual appearance. Prospectively, new databases can be set up and comparative studies between different datasets become possible. 2 Literature Review 2.1 Elimination ofLabels Labels are valuable components in historical maps holding important metadata. However, text within a map is typically seen as a disturbing factor when extracting geometries. Misinterpretations in the context of segmentation may easily arise due to overlaps, direct adjacencies, or similar color values to map elements and structures such as lines or textures (Heitzler and Hurni 2020; Bhowmik etal. 2018; Chiang 2017). Monochrome maps, in particular, have a reduced number of parameters to differentiate between text and other elements. However, an initial elimination of text or labels from historical maps can be seen as a major advantage for further object extraction processes (Gede etal. 2020). Previous attempts identified labels with the help of text recognition—subsequent to object recognition and vectorization—or by shape recognition algorithms (Iosifescu etal. 2016). Chrysovalantis and Nikolaos (2020) used binarized maps to separate text from other objects (see also Bhowmik etal. (2018)). By eliminating small pixel groups, they were able to remove letters. A GRASS GIS add-on developed by Gobbi etal. (2019) and Zatelli etal. (2019) replaces relevant pixel values by means of low-pass filters within old cadaster maps. However, pixels must already be defined as “text” in advance. Telea (2004) and Bertalmío etal. (2001) suggest different image inpainting techniques, which are often applied for image restoration. Missing or damaged image regions are filled to create an image without giving the viewer a hint of changes. In our testing, these approaches caused an unsatisfactory blurring of the input image. 2.2 Object‑Based Image Analysis Many methodologies for (semi-)automated object extraction from historical maps were demonstrated in recent years but proven insufficient for various reasons. For instance, a common histogram thresholding or color space clustering (Herrault etal. 2013) ignores any spatial context, whereas artificial neural networks require an inadequate amount of training data (Gobbi etal. 2019). Chrysovalantis and Nikolaos (2020) used GIS functionalities to convert a historical multicolor map into a binary image and then to extract and vectorize geometries of buildings. However, textured or corrupt polygons could not be handled and labels were eliminated only partially. A similar approach was conducted by Iosifescu etal. (2016). By combining GIS operations with Python libraries, Gede etal. (2020) segmented and vectorized geometries of rivers as a function of their color whereas Le Riche (2020) extracted buildings from historical maps based on colors and textures. Zatelli etal. (2019) and Gobbi etal. (2019) used GIS and R to segment and classify features from historical land use maps by regarding their colors, sizes, and shapes. Additional machine learning techniques were applied by Gobbi etal. (2019). In recent years, deep learning attempts via convolutional neural networks (CNNs) “have recently received considerable attention in object recognition, classification, and detection tasks” (Uhl etal. 2017) from historical maps (Jiao etal. 2020, Heitzler and Hurni 2020, and Xydas etal. 2022). However, they suffer from major drawbacks. Results from CNNs strongly depend on the quality and generally low quantity of available training data. Often, these data stocks are created manually and solely on the basis of the input bitmap itself, which is time-consuming and impedes an applicability. Originating from the field of remote sensing, geographic object-based image analysis may also be applied to scans of maps (Hay and Castilla 2008). In the broad field of cartography, only few authors use OBIA approaches to create new geodata. Whereas Dornik etal. (2016) reproduced soil maps from climate and vegetation maps, Kerle and de Leeuw (2009) extracted point-based population data from paper maps to estimate long-term population growth. Edler etal. (2014) applied OBIA to extract and quantify the presence of roads, buildings, and land use classes and to further evaluate the complexity of topographic maps thereby. In contrast to pixel-wise approaches, OBIA regards not only spectral information, but also, e.g., the shape, size, or neighborly relations of objects, and is, therefore, much closer to human perception. Hence, OBIA is often suggested for object extraction from historical maps with the aim to make them machine-interpretable (Blaschke etal. 2014). Many studies in the field of OBIA focus on maps of colors and smaller scales, presuppose a preceding georeferencing (Chrysovalantis and Nikolaos 2020; Gede etal. 2020; Iosifescu etal. 2016) or well-defined shapes of objects (Chrysovalantis and Nikolaos 2020; Gobbi etal. 2019; Heitzler and Hurni 2020), or disregard intersections between map features. 6 KN - Journal of Cartography and Geographic Information (2023) 73:3–18 1 3 2.3 Vectorization andVector Enhancement As vector data can be better processed and analyzed than raster data, a majority of the mentioned authors proceed with a vectorization of extracted map objects. Brown (2002) and Arteaga (2013) use specific software tools to, respectively, vectorize the outlines of geologic structures and buildings from historical maps. Vectorization tools are also provided within ArcGIS, GRASS GIS (Gede etal. 2020), and the GDAL library (Jiao etal. 2020). To purge vectorized objects, further simplification processes may follow. Multiple software and tools, including eCognition, QGIS, ArcGIS (Godfrey and Eveleth 2015), SAGA GIS (Gede etal. 2020), R (Arteaga 2013), and Python libraries, implement pre-built functions to smooth or simplify lines or polygons and to remove outliers, spikes, and other artifacts. 2.4 Object Matching For the direct comparison of vector objects from different maps from various times, distance and similarity measures may be promising (Xavier etal. 2016). Matching geometries between different inputs is frequently performed on the basis of shape or spatial similarities (Tang etal. 2008) or identical attribute values (Frank and Ester 2006). However, semantic similarity approaches are not feasible as scanned historical maps usually hold no ancillary information. Even if names of roads or buildings were available—e.g., by a preceding text recognition—they would need to be assigned to their corresponding geometries. When analyzing geometric relations, such as overlapping areas or distance measures (e.g., Euclidian or Hausdorff distance), only relative distances between objects are considered. This technique is useless when comparing not yet georeferenced datasets (Xavier etal. 2016). Region-based shape descriptors (e.g., area, convex hull, Moment or Grid descriptor, see Ahmad etal. (2014)) regard all pixels within a shape and may therefore be promising for a comparison between identical real-world objects from different inputs. But due to uncertainties, they are rather considered complementary matching approaches. Additional similarity measures are necessary (Xavier etal. 2016). By regarding the spatial relationship between objects, Stefanidis etal. (2002) quantified their distances and relative positions. Samal etal. (2004) and Kim etal. (2010) consulted third objects to create an overall geographic context. Also, Sun etal. (2021) regarded spatial relationships by linking identical real-world objects from different historical maps. However, their knowledge graph approach presupposes the existence and assignment of labels to their corresponding geometries. 3 Data For a proof of concept of our suggested methodologies, a large-scale (~ 1:11,000) historical map from the middle of the nineteenth century was chosen, which has already been object of research within related studies (Schlegel 2019, 2021). The original non-georeferenced and undistorted version of the map scan was cropped to a smaller extent (~ 1000 × 800m in reality) for reasons of runtime compression within all processes. No map projection is known. The map subset in Fig.1 shows the city center of Hamburg with blocks of buildings, roads, and water areas. Apart from subsequently colorized water areas, the map is drawn in black and white. Many data suppliers provide their raster scans with a resolution of 300 ppi which is considered adequate for object extraction purposes (Pearson etal. 2013). Lower pixel densities induce blurring and pixelation, whereas higher values tend to highlight interfering artifacts from, e.g., folds in paper, discolorations, or smudges (Peller 2018). We continued to work with the TIFF format (without compression) as it is lossless concerning the image’s original pixel values (Gede etal. 2020). To demonstrate the transferability of the workflow, two more large-scale historical maps covering the same spatial area were used in the further course (see Fig.9a, b). They all differ in their visual appearance and complexity in terms of contrasts, textures, or the existence of labels and gridlines. For comparing the described data to a current counterpart, official vector datasets including recent polygonal buildings (Landesbetrieb Geoinformation und Vermessung 2022) and line-type roads (Behörde für Verkehr und Mobilitätswende (BVM) 2020) were used. 4 Object Extraction 4.1 Preparation fortheElimination ofLabels As similar color values and overlaps between labels and other map objects impede a clear discriminability, an initial elimination of labels designating real-world objects significantly contributes to a facilitation of object recognition processes. We suggest to make use of the output from previous label detection attempts (see Schlegel (2021)): vector bounding boxes comprising text image areas, which can be seen in Fig.1. An exemplary text image area is shown in Fig.2a. With the aim to eliminate its content from the map, it was initially cropped by means of its original bounding box (see Fig.2b) and rotated to the horizontal by its angle of alignment (Fig.2c)—calculated by the used text detection tool Strabo (Li etal. 2018; Chiang and Knoblock 2014). However, these text image areas do not only include characters, 7KN - Journal of Cartography and Geographic Information (2023) 73:3–18 1 3 but also edges of buildings, which is an outgrowth of Strabo (see upper margin in Fig.2c). This is counterproductive within the subsequent step of building segmentation as these image areas were supposed to be entirely eliminated from the map. Thus, building edges would become distorted. To retain these important edges, all pixels within a bounding Fig. 1 Map subset showing the city center of Hamburg (Harvard Map Collection, Harvard College Library etal. (n.d.)) with bounding boxes containing labels produced by a previous text detection Fig. 2 Steps for separating building edges from labels shown with an exemplary dataset: a input map with bounding box containing text image area, which then was b cropped, c aligned horizontally, and d converted into a binary as well as e athree-class mask. The f resulting bounding box excluding building edges was g turned back to its original orientation 8 KN - Journal of Cartography and Geographic Information (2023) 73:3–18 1 3 box were differentiated by text and parts of buildings. A user-defined thresholding helped to generate a binary mask consisting of dark “foreground” and bright “background” pixels (see Fig.2d). A further “foreground” differentiation was needed to separate building edges from text pixels. However, similar color values, overlaps, and smooth transitions between text and buildings were challenging. For reclassifying former “foreground” into either “text” or “building edge” pixels, multiple thresholds and conditions had to be applied (Fig.2e). As labels designating roads most commonly run parallel to nearby building edges, this step was performed row-wise. As Fig.2f indicates, all pixels representing “text” and “background” were combined and vectorized. The resulting polygonal bounding box was turned back by its initial rotation angle (see Fig.2g) and then used within the following object extraction steps. 4.2 Object Detection andRecognition To detect homogeneous image regions and extract objects such as buildings or water areas from large-scale historical maps, we used object-based image analysis. In contrast to pixel-based approaches (e.g., Maximum Likelihood, Clustering, or Thresholding), which only regard spectral differences between pixels, OBIA generates image objects also based on common textures, shapes, context, etc. and is, therefore, more suitable for historical maps with limited spectral information and heterogeneous appearances (Blaschke etal. 2014; Hussain etal. 2013). As none of the many free and open source packages available for semi-automated feature extraction produces comparable results, we made use of the proprietary software eCognition Developer 10.2 to generate GIS compatible data from a historical map via OBIA (Kaur and Kaur 2014). eCognition converts user-defined rule sets—built-up from functions, filters, statistics, etc. for image segmentation and classification—into machine-readable code. These concatenations of algorithms can be easily transferred to other images (Trimble Inc. 2022). As Fig.3a indicates, a first rough differentiation between dark (foreground) map features (e.g., buildings and labels) and the map’s bright background (water areas, roads, and places) was enabled by thresholding the input TIFF. The content of the labels’ bounding boxes, as shown in Fig.2f, was simply classified as “background” and could therefore be eliminated (see Fig.3b). The detection of further map objects is therefore significantly facilitated on the one hand and building edges remain unaltered on the other hand. To extract contours of buildings, an edge detector was applied to the image. The building texture’s repeating pattern could be detected by means of a gray-level co-occurrence matrix—which measures the vertical invariance of adjacent pixel pairs—and analyzed by texture descriptors (Chaves 2021; Trimble Inc. 2021). Regarding the original map in Fig.1, public buildings (e.g., the townhall or churches) have a significantly darker texture and could, therefore, clearly be differentiated from other buildings based on their gray values. Water areas were identified by thresholding the RGB blue channel as well as applying supplementary texture descriptors to avoid false positives. 4.3 Vectorization Generally, OBIA results in raster files containing individual image objects, subdivided into predefined single classes. For further processing and analysis purposes, a vectorization of this data is inevitable. Based on experiences of Iosifescu etal. (2016) and Arteaga (2013), we applied GDAL’s polygonize function to perform a raster-to-vector conversion Fig. 3 Foreground objects separated from the map’s background a before and b after eliminating labels 9KN - Journal of Cartography and Geographic Information (2023) 73:3–18 1 3 for each map class. Several functions to simplify and smooth the vectorized map features, to close inlying minor gaps, and eliminate small isolated polygons were compiled within an end-to-end Python script. This way, interfering artifacts (e.g., islands, protrusions, or spikes) stemming from an imprecise segmentation or undetected labels could be handled. The resulting polygons representing (public) buildings and water areas are shown in Fig.4 and can be processed within future analysis operations. 5 Linking Historical andCurrent Datasets Compared to previous studies dealing with object extraction from historical maps, we go one step further and present an exemplary way of how qualitative and quantitative evaluations of long-term changes within a cityscape may be practically enabled. We therefore spatially assigned a more recent vector dataset to the historical counterpart as shown in Fig.7. Our aim was to automate this coarse georeferencing process as far as possible. Due to changing names of roads and buildings over time, the lack of indepth information, or simply imprecise scales, distances, and directions within historical maps, we used the previously extracted geometries for georeferencing purposes (Rumsey and Williams 2002). As can be seen from Fig.5, churches and other municipal buildings still exist over time and, beyond that, do not substantially change their basic shape and geographic location over time. Therefore, their object shapes could be matched and used for the definition of control points in the further course of georeferencing (Skopyk 2021; Havlicek and Cajthaml 2014). 5.1 Shape Matching To define matching georeferencing control points between the historical and current dataset, identical real-world objects are to be identified. We, therefore, measured the shape similarity between the extracted public buildings shown in Fig.5 (Sun etal. 2021; MacEachren 1985). A matching based on Fig. 4 Vectorized and revised features of the historical map 10 KN - Journal of Cartography and Geographic Information (2023) 73:3–18 1 3 spatial or semantic (attribute-based) similarities was impractical due to the lack of a coordinate system as well as further information concerning the historical map. As Fig.5 indicates, a side-by-side comparison between geometries of public buildings extracted from the historical map on the one hand and the official vector dataset containing current buildings on the other hand was performed. We implemented a matching of their shapes based on their Intersection over Union (IoU). After adjusting the aspect ratios of corresponding counterparts via rectangular bounding boxes (“envelopes” (Esri 2022)), their respective deviations could be quantified via IoU. As can be seen from Fig.6, a building geometry and its envelope together form a binary mask—consisting of the values 1 (building geometry) and 0 (envelope). A final superimposition of these masks helped to determine their overlapping area (intersection) proportionally to their common area (union) (see Fig.6). All “building” pixels with a value of 1 were considered for the IoU calculation, which was conducted with the help of Python’s numpy library. Table1 summarizes the IoU results for all detected public buildings continued to use for georeferencing purposes. 5.2 Georeferencing 5.2.1 Method Overview The centroids of those geometries with the closest matches (see highlighted cells in Table1) were defined as control points for a semi-automated, rough georeferencing between the historical and current dataset. To preserve the objects’ shapes and to keep spatial deformations to a minimum within the historical data, an affine transformation of all current buildings and roads was conducted. This Fig. 5 Vectorized public buildings (churches and townhall) from the historical map (upper row) and their counterparts from the current dataset (bottom row) Fig. 6 Intersection over Union between the historical St. Petri Kirche and a its current counterpart as well as b the current St. Katharinen Kirche. The aspect ratio of the geometries’ envelopes was adjusted to one another, respectively 11KN - Journal of Cartography and Geographic Information (2023) 73:3–18 1 3 was done via QGIS Vector Bender (Dalang 2019) using the three matching object pairs highlighted in Table1 as well as Fig.7. In our test case, only three control points with sufficient pointing accuracy could be found—such a small number is quite typical for historical maps. However, if available, a larger quantity of control points is advisable Table 1 Numerical results from Intersection over Union between historical and current buildings’ geometries Historical map St. Katharinen Kirche St. Petri Kirche Rathaus Current dataset St. Katharinen Kirche 83,9% 74,9% 45,0% St. Petri Kirche 79,3% 84,4% 43,1% Rathaus47,5% 45,9% 58,5% St. Jacobi Kirche 82,1% 80,2% 42,6% Mahnmal St. Nikolaia54,0% 49,8% 26,1% aThe St. Jacobi Kirche was not classified as public building by eCognition whereas the (Mahnmal) St. Nikolai was reconstructed in another city district after being mainly destroyed during World War II and leaving only its tower until today (Claussen n.d.). a The St. Jacobi Kirche was not classified as public building by eCognition whereas the (Mahnmal) St. Nikolai was reconstructed in another city district after being mainly destroyed during World War II and leaving only its tower until today (Claussen n.d.) Fig. 7 Georeferenced current buildings and roads based on the centroids of the highlighted St.-Katharinen-Kirche, St.-Petri-Kirche, and Rathaus 18 KN - Journal of Cartography and Geographic Information (2023) 73:3–18 1 3 Peller P (2018) From paper map to geospatial vector layer: demystifying the process. IASSIST Q 42(3):1–24 Rumsey D, Williams M (2002) Historical maps in GIS. In: Knowles AK (ed) Past time, past place: GIS for history. Esri Press, Redlands, CA, pp 1–18 Samal A, Seth S, Cueto K (2004) A feature-based approach to conflation of geospatial sources. IJGIS 18(5):459–489. https:// doi. org/ 10. 1080/ 13658 81041 00016 58076 Sammlung Christian Terstegge (n.d.) 1722, von C. Fritzsch, photo-lithographisches Replikat vom Verlag Strumper & Co., 1880. https:// www. c hris tianterst egg e. de/ hambu rg/ karten_ hambu r g/ files/ 1722_ fritz sch_ strum per_ 300dpi. jpeg. Accessed 4 Feb 2022 Schlegel I (2019) Empirical study for a deployment of a methodology for improving the comparability between historical and current maps. KN - J Cartogr Geogr Info 69(2):121–130. https:// doi. org/ 10. 1007/ s4248901900016-0 Schlegel I (2021) Automated extraction of labels from large-scale historical maps. AGILE GIScience Series. https:// doi. org/ 10. 5194/ agilegiss-2122021 Skopyk B (2021, March 8) Georeferencing Historical Maps: Methods, best practices, and a tutorial in ArcGIS Pro. ArcGIS StoryMaps. https:// story maps. arcgis. com/ stori es/ dd75d 0398f 7d4de d924d 30316 1895b 8b. Accessed 30 June 2022 Stefanidis A, Agouris P, Georgiadis C, Bertolotto M, Carswell JD (2002) Scaleand orientation-invariant scene similarity metrics for image queries. IJGIS 16(8):749–772. https:// doi. org/ 10. 1080/ 13658 81021 01485 52 Sun K, Hu Y, Song J, Zhu Y (2021) Aligning geographic entities from historical maps for building knowledge graphs. IJGIS 35(10):2078–2107 Tang W, Hao Y, Zhao Y, Li N (2008) Feature matching algorithm based on spatial similarity. In: Proceedings of SPIE 7147, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Classification of Remote Sensing Images, 714704. https:// doi. org/ 10. 1117/ 12. 813204 Telea A (2004) An image inpainting technique based on the fast marching method. JGT 9(1):25–36. https:// doi. org/ 10. 1080/ 10867 651. 2004. 10487 596 Trimble Inc. (2021) Haralick texture. https:// docs. ecogn ition. com/ v10.0. 2/# eCogn ition_ docum entat ion/ Refer ence Book/03 Features/2 Object features/4 Texture/Haralick texture. htm?Highlight=haralick. Accessed 25 May 2022 Trimble Inc. (2022) The Power of eCognition. https:// docs. ecogn ition. com/# eCogn ition_ docum entat ion/ Modul es/1 eCognition at a glance/01 Introduction to the Power of eCognition.htm. Accessed 24 May 2022 Uhl JH, Leyk S, Chiang YY, Duan W, Knoblock CA (2017) Extracting Human Settlement Footprint from Historical Topographic Map Series Using Context-Based Machine Learning. In: Proceedings of the 8th International Conference of Pattern Recognition Systems. https:// doi. org/ 10. 1049/ cp. 2017. 0144 Xavier EMA, Ariza-López FJ, Ureña-Cámara MA (2016) A survey of measures and methods for matching geospatial vector datasets. ACM Comput Surv 49(2):1–34. https:// doi. or g/ 10. 1145/ 29631 47 Xydas C, Kesidis A, Kalogeropoulos K, Tsatsaris A (2022) Buildings Extraction from Historical Topographic Maps via a Deep Convolution Neural Network. In: Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications 5, pp 485–492. https:// doi. or g/ 10. 5220/ 00108 39700 003124 Zatelli P, Gobbi S, Tattoni C, La Porta N, Ciolli M (2019) Object-based image analysis for historic maps classification. Int Arch Photogramm Remote Sens Spat Inf Sci XLII-4/W14:247–254