hantian/layoutreader is a token-classification model based on LayoutLMv3 that predicts the correct reading order for bounding boxes extracted from PDFs or detected via OCR. It converts unordered layout elements into a coherent, human-readable sequence. The model is distributed as open weights on Hugging Face and integrates with the Transformers library.
In the Other AI space, Layoutreader takes a focused approach. It focuses on determining the correct sequential reading order of text regions detected in document images or PDFs. Layoutreader is an open-source project aimed at document AI developers. The project is open source (Open Source). Layoutreader is available on the web and API.
Behind Layoutreader is Hantian, and it first shipped in 2024. Development happens publicly on GitHub with 322 stars. Key capabilities include Reading Order Prediction, Token Classification, and PDF Layout Analysis.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match