Novel and Effective CNN-Based Binarization for Historically Degraded As-built Drawing Maps
This work addresses a specific challenge in document image processing for historical archives, offering an incremental improvement in binarization techniques for degraded maps.
The paper tackles the problem of binarizing historically degraded as-built drawing maps by removing artifacts like noise, yellowing, and folded lines while preserving foreground components, and demonstrates that their CNN-based method substantially outperforms nine existing methods in accuracy, PSNR, and perceptual effect, with significant execution-time reduction compared to retrained state-of-the-art CNN methods.
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.