Automatic Search of Multiword Place Names on Historical Maps

TL;DR

This paper uses existing methods to recognize words on historical maps to link single-word text labels into potential multiword phrases by constructing minimum spanning trees, and evaluates the accuracy of the minimum spanning tree approach at linking multiword place names.

Abstract

Historical maps are invaluable sources of information about the past, and scanned historical maps are increasingly accessible in online libraries. To retrieve maps from these large libraries that contain specific places of interest, previous work has applied computer vision techniques to recognize words on historical maps, enabling searches for maps that contain specific place names. However, searching for multiword place names is challenging due to complex layouts of text labels on historical maps. This paper proposes an efficient query method for searching a given multiword place name on historical maps. Using existing methods to recognize words on historical maps, we link single-word text labels into potential multiword phrases by constructing minimum spanning trees. These trees aim to link pairs of text labels that are spatially close and have similar height, angle, and capitalization. We then query these trees for the given multiword place name. We evaluate the proposed method in two experiments: 1) to evaluate the accuracy of the minimum spanning tree approach at linking multiword place names and 2) to evaluate the number and time range of maps retrieved by the query approach. The resulting maps reveal how places using multiword names have changed on a large number of maps from across history.

Figures (4)

• Figure 1: Challenges of linking together multiword place names on historical maps.
• Figure 2: An overview of our method for searching a multiword place name in a given set of text labels from a historical map.
• Figure 3: Visualization of linkage graphs constructed from map text labels the character distance threshold baseline (left) and our method (right). The colors of the bounding boxes indicate: $\square$: correctly linked multiword phrase $\square$: single word $\square$: incorrectly linked multiword phrase.
• Figure 4: Maps sampled from a time-sequenced map query for "Sault Ste. Marie".