Translator Disclaimer
Paper
20 December 2021 Self-supervised degraded document image binarization method based on second-order central moments and multi-scale network
Jinlu Zhang, Liyu Lin, Changlong Jin
Author Affiliations +
Proceedings Volume 12155, International Conference on Computer Vision, Application, and Design (CVAD 2021); 121550O (2021) https://doi.org/10.1117/12.2626563
Event: International Conference on Computer Vision, Application, and Design (CVAD 2021), 2021, Sanya, China
Abstract
In this work, we propose an effective self-supervised method for document image binarization. The proposed method is based on image second-order central moment and multi-scale convolution neural network (CNN). It effectively binarizes document images by addressing degradation issues (such as uneven illumination, ink stain, and fading). We first remove noticeable noise and performs data normalization in preprocessing step. Then the pseudo binarization image is generated by the second-order central moment algorithm. Then a multi-scale self-supervised network is utilized to distinguish the foreground (character) from the degraded image (background). We combine traditional image processing and selfsupervised networks to ensure the efficiency and effectiveness of the method while improving the generalization ability on multiple data sets. Extensive experiments show that the proposed model performs best in DIBCO benchmarks.
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jinlu Zhang, Liyu Lin, and Changlong Jin "Self-supervised degraded document image binarization method based on second-order central moments and multi-scale network", Proc. SPIE 12155, International Conference on Computer Vision, Application, and Design (CVAD 2021), 121550O (20 December 2021); https://doi.org/10.1117/12.2626563
PROCEEDINGS
8 PAGES


SHARE
Advertisement
Advertisement
KEYWORDS
Convolution

Image enhancement

Neural networks

Frequency modulation

Machine learning

Convolutional neural networks

Signal to noise ratio

Back to Top