Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

A Repo For Document AI

ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

Detectron2 for Document Layout Analysis

[Late Submission] Solution for Kuzushiji recognition (Kaggle competition)

Visual Domain Knowledge-based Multimodal Zoning Textual Region Localization in Noisy Historical Document Images

Extracting structured text from GI Bill index cards for JDoc 2023 paper

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Analyze document image complexity based on segmentation results

Matrix Representation reformats images as RDF using natural ⨯ natural coordinates as a Media-Signature-Record / Structured-Data-Description. It is a positive, productive, and pragmatic introduction to semantic-web programming.