NLP group

Robust Grid Detection in Historical Map Images

Josef Baloun and Ladislav Lenc and Pavel Král
2022 IEEE International Conference on Image Processing (ICIP) (2022)

PDF

Abstract

This paper presents a novel method for grid detection in historical maps. The approach is based on Hough transform accompanied with a sophisticated post-processing. They are applied to detect the grid that consists of graticule lines. It works without any training and does not require any annotated data. The proposed approach is very efficient in detecting the rectangular grid and the intersection points as shown in the international "MapSeg" segmentation competition, where it won the Task 3 with a significant margin. The robustness of the proposed method has been demonstrated by evaluating on another dataset composed of significantly different cadastral map images with excellent results.