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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

To efficiently extract textual information from color degraded documentimages is a significant research area. The prolonged imperfect preservation ofancient documents has led to various types of degradation, such as pagestaining, paper yellowing, and ink bleeding. These types of degradation badlyimpact the image processing for features extraction. This paper introduces anovelty method employing generative adversarial networks based on color channelusing discrete wavelet transform (CCDWT-GAN). The proposed method involvesthree stages: image preprocessing, image enhancement, and image binarization.In the initial step, we apply discrete wavelet transform (DWT) to retain thelow-low (LL) subband image, thereby enhancing image quality. Subsequently, wedivide the original input image into four single-channel colors (red, green,blue, and gray) to separately train adversarial networks. For the extraction ofglobal and local features, we utilize the output image from the imageenhancement stage and the entire input image to train adversarial networksindependently, and then combine these two results as the final output. Tovalidate the positive impact of the image enhancement and binarization stageson model performance, we conduct an ablation study. This work compares theperformance of the proposed method with other state-of-the-art (SOTA) methodson DIBCO and H-DIBCO ((Handwritten) Document Image Binarization Competition)datasets. The experimental results demonstrate that CCDWT-GAN achieves a toptwo performance on multiple benchmark datasets. Notably, on DIBCO 2013 and 2016dataset, our method achieves F-measure (FM) values of 95.24 and 91.46,respectively.

CCDWT-GAN: Generative Adversarial Networks Based on Color Channel Using Discrete Wavelet Transform for Document Image Binarization