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

In the rapidly evolving digital era, the analysis of document layouts plays apivotal role in automated information extraction and interpretation. In ourwork, we have trained MViTv2 transformer model architecture with cascaded maskR-CNN on BaDLAD dataset to extract text box, paragraphs, images and tables froma document. After training on 20365 document images for 36 epochs in a 3 phasecycle, we achieved a training loss of 0.2125 and a mask loss of 0.19. Our workextends beyond training, delving into the exploration of potential enhancementavenues. We investigate the impact of rotation and flip augmentation, theeffectiveness of slicing input images pre-inference, the implications ofvarying the resolution of the transformer backbone, and the potential ofemploying a dual-pass inference to uncover missed text-boxes. Through theseexplorations, we observe a spectrum of outcomes, where some modificationsresult in tangible performance improvements, while others offer unique insightsfor future endeavors.

Document Layout Analysis on BaDLAD Dataset: A Comprehensive MViTv2 Based Approach