English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Document image enhancement and binarization methods are often used to improvethe accuracy and efficiency of document image analysis tasks such as textrecognition. Traditional non-machine-learning methods are constructed onlow-level features in an unsupervised manner but have difficulty withbinarization on documents with severely degraded backgrounds. Convolutionalneural network-based methods focus only on grayscale images and on localtextual features. In this paper, we propose a two-stage color document imageenhancement and binarization method using generative adversarial neuralnetworks. In the first stage, four color-independent adversarial networks aretrained to extract color foreground information from an input image fordocument image enhancement. In the second stage, two independent adversarialnetworks with global and local features are trained for image binarization ofdocuments of variable size. For the adversarial neural networks, we formulateloss functions between a discriminator and generators having an encoder-decoderstructure. Experimental results show that the proposed method achieves betterperformance than many classical and state-of-the-art algorithms over theDocument Image Binarization Contest (DIBCO) datasets, the LRDE DocumentBinarization Dataset (LRDE DBD), and our shipping label image dataset. We planto release the shipping label dataset as well as our implementation code atgithub.com/opensuh/DocumentBinarization/.

Two-stage generative adversarial networks for document image binarization with color noise and background removal