Novel and Effective CNN-Based Binarization for Historically Degraded As-built Drawing Maps

TL;DR

This paper introduces a CNN-based binarization technique for degraded historical maps, effectively removing artifacts while preserving details, and demonstrates superior accuracy and efficiency over existing methods.

Contribution

A semi-automatic labeling method for dataset creation and a novel CNN-based binarization approach that outperforms existing methods in accuracy and speed.

Findings

Outperforms nine existing binarization methods in accuracy and PSNR.

Significantly reduces execution time compared to state-of-the-art CNN methods.

Creates a new dataset of HDAD pairs for training and evaluation.

Abstract

Binarizing historically degraded as-built drawing (HDAD) maps is a new challenging job, especially in terms of removing the three artifacts, namely noise, the yellowing areas, and the folded lines, while preserving the foreground components well. In this paper, we first propose a semi-automatic labeling method to create the HDAD-pair dataset of which each HDAD-pair consists of one HDAD map and its binarized HDAD map. Based on the created training HDAD-pair dataset, we propose a convolutional neural network-based (CNN-based) binarization method to produce high-quality binarized HDAD maps. Based on the testing HDAD maps, the thorough experimental data demonstrated that in terms of the accuracy, PSNR (peak-signal-to-noise-ratio), and the perceptual effect of the binarized HDAD maps, our method substantially outperforms the nine existing binarization methods. In addition, with similar accuracy, the experimental results demonstrated the significant execution-time reduction merit of our method relative to the retrained version of the state-of-the-art CNN-based binarization methods.