DevashishPrasad/CascadeTabNet

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1549 stars · 425 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

CascadeTabNet is a PyTorch/mmdetection implementation of a CVPR 2020 paper for end-to-end table detection and structure recognition from image-based documents. It uses a Cascade mask R-CNN HRNet model to detect table regions and recognize body cell structure in a single CNN pass.

Use cases

• detect tables in scanned document images
• extract table structure from pdf page images
• recognize table cells in research paper screenshots
• run table detection on ICDAR 2013/2019 datasets
• benchmark table recognition models
• convert image-based tables into structured data

When to choose

• you need state-of-the-art table detection and cell structure recognition from document images
• you want to reproduce or build on the CascadeTabNet CVPR 2020 paper
• your pipeline already uses PyTorch and mmdetection v1.2

When to avoid

• you need a maintained production library with recent dependency support
• you work with native digital PDFs rather than image-based documents
• you cannot pin old versions of PyTorch, mmcv, and mmdetection

Facets

library · maturity maintenance

computer-vision ocr machine-learning deep-learning pdf computer-vision pdf machine-learning deep-learning python table-detection table-structure-recognition document-image-analysis mmdetection pytorch research-code linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="DevashishPrasad/CascadeTabNet")