# Layout-Parser/layout-parser

A Unified Toolkit for Deep Learning Based Document Image Analysis

Repository: https://github.com/Layout-Parser/layout-parser
Canonical: https://ross.abutalabs.com/products/layout-parser
Homepage: https://layout-parser.github.io/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: layout-analysis, deep-learning, object-detection, ocr, layout-parser, detectron2, document-layout-analysis, computer-vision, document-image-processing, layout-detection
Last push: 2024-08-15T06:26:34+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2275, "days_push": 748, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5774, forks 532 (observed 2026-08-28T04:09:29.478859+00:00)

## What it is
LayoutParser is a Python toolkit for deep learning based document image analysis, offering unified APIs for layout detection models, layout data structures, OCR integration, and visualization. It includes a model zoo of pre-trained layout detection models loadable in a few lines of code.

## Use cases
- detect text blocks and layout regions in scanned documents
- extract document structure from pdf page images
- run ocr on detected layout regions
- train custom document layout detection models
- visualize bounding boxes of document elements
- parse tables and figures from research paper images

## When to choose
- you need deep-learning-based document layout analysis in Python
- you want a unified API over multiple pre-trained layout detection models
- you need to combine layout detection with OCR pipelines

## When to avoid
- you only need simple text extraction from digital PDFs without layout models
- you need a maintained project with frequent updates
- you work outside Python or need GPU-free lightweight inference

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, ocr, image-processing, machine-learning, deep-learning, pdf
- domain: computer-vision, machine-learning
- platform: python, cross-platform
- tags: layout-detection, document-image-analysis, detectron2, object-detection, pretrained-models, document-parsing, document-layout-analysis, natural-language-processing

## Member repositories
- Layout-Parser/layout-parser (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:29.478859+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:52:52.253212+00:00, confidence not recorded.
  - readme: https://github.com/Layout-Parser/layout-parser (fetched 2026-08-28T04:09:29.478859+00:00, sha d7018d28e731)
  - homepage: https://layout-parser.github.io/ (fetched 2026-08-29T08:48:10.793261+00:00, sha 74851bdf4b00)
- Data as of 2026-08-30T08:39:29.467469+00:00.