Detecting Omissions in Geographic Maps through Computer Vision

TL;DR

This paper presents a computer vision method using CNNs and transfer learning to automatically detect and verify geographic maps and landmarks, addressing challenges posed by diverse map styles.

Contribution

It introduces a novel approach combining CNNs and text recognition for map verification and presents the VinMap dataset for training and testing.

Findings

Achieved 85.51% F1-score in map and landmark detection

Developed a new dataset, VinMap, for geographic map analysis

Demonstrated practical utility of the method in real-world map verification

Abstract

This paper explores the application of computer vision technologies to the analysis of maps, an area with substantial historical, cultural, and political significance. Our focus is on developing and evaluating a method for automatically identifying maps that depict specific regions and feature landmarks with designated names, a task that involves complex challenges due to the diverse styles and methods used in map creation. We address three main subtasks: differentiating maps from non-maps, verifying the accuracy of the region depicted, and confirming the presence or absence of particular landmark names through advanced text recognition techniques. Our approach utilizes a Convolutional Neural Network and transfer learning to differentiate maps from non-maps, verify the accuracy of depicted regions, and confirm landmark names through advanced text recognition. We also introduce the VinMap dataset, containing annotated map images of Vietnam, to train and test our method. Experiments on this dataset demonstrate that our technique achieves F1-score of 85.51% for identifying maps excluding specific territorial landmarks. This result suggests practical utility and indicates areas for future improvement.