Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/21706
Title: UdbNet: Unsupervised document binarization network via adversarial game
Authors: Kumar A.
Ghose S.
Chowdhury P.N.
Pratim Roy, Partha
Pal U.
Published in: Proceedings - International Conference on Pattern Recognition
25th International Conference on Pattern Recognition, ICPR 2020
Abstract: Degraded document image binarization is one of the most challenging tasks in the domain of document image analysis. In this paper, we present a novel approach towards document image binarization by introducing three-player min-max adversarial game. We train the network in an unsupervised setup by assuming that we do not have any paired-training data. In our approach, an Adversarial Texture Augmentation Network (ATANet) first superimposes the texture of a degraded reference image over a clean image. Later, the clean image along with its generated degraded version constitute the pseudo paired-data which is used to train the Unsupervised Document Binarization Network (UDBNet). Following this approach, we have enlarged the document binarization datasets as it generates multiple images having same content feature but different textual feature. These generated noisy images are then fed into the UDBNet to get back the clean version. The joint discriminator which is the third-player of our three-player min-max adversarial game tries to couple both the ATANet and UDBNet. The three-player min-max adversarial game stops, when the distributions modelled by the ATANet and the UDBNet align to the same joint distribution over time. Thus, the joint discriminator enforces the UDBNet to perform better on real degraded image. The experimental results indicate the superior performance of the proposed model over existing state-of-the-art algorithm on widely used DIBCO datasets. The source code of the proposed system is publicly available at https://github.com/VIROBO-15/UDBNET. © 2021 IEEE
Citation: Proceedings - International Conference on Pattern Recognition (2020): 7817-7824
URI: https://doi.org/10.1109/ICPR48806.2021.9412442
http://repository.iitr.ac.in/handle/123456789/21706
Issue Date: 2020
Publisher: Institute of Electrical and Electronics Engineers Inc.
Keywords: Textures
Degraded document images
Degraded images
Document image analysis
Document image binarization
Joint distributions
Reference image
State-of-the-art algorithms
Textual features
Pattern recognition
ISBN: 9.78173E+12
ISSN: 10514651
Author Scopus IDs: 57219788107
57209826260
57212494902
56880478500
57200742116
Author Affiliations: Kumar, A., Techno Main Salt Lake, Sector V, Kolkata, India
Ghose, S., Institute of Engineering and Management, Kolkata, India
Chowdhury, P.N., Indian Statistical Institute, Kolkata, India
Roy, P.P., Indian Institute of Technology Roorkee, India
Pal, U., Indian Statistical Institute, Kolkata, India
Corresponding Author: Kumar, A.; Techno Main Salt Lake, Sector V, India; email: kumar.amandeep015@gmail.com Ghose, S.; Institute of Engineering and ManagementIndia; email: shuvozit.ghose@gmail.com
Appears in Collections:Conference Publications [CS]

Files in This Item:
There are no files associated with this item.
Show full item record


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.