Search Results for "vision"

DeepSeek-OCR is an open-source optical character recognition solution built as part of the broader DeepSeek AI vision-language ecosystem. It is designed to extract text from images, PDFs, and scanned documents, and integrates with multimodal capabilities that understand layout, context, and visual elements beyond raw character recognition. The system treats OCR not simply as “read the text” but as “understand what the text is doing in the image”—for example distinguishing captions from body text, interpreting tables, or recognizing handwritten versus printed words. ...

Nougat is a multi-modal generative modeling framework that bridges vision and text modalities with structured generation control (e.g. layout, scene composition) rather than treating images as flat contexts. It combines object-centric modules with transformer-based reasoning to propose, refine, and render scenes in a generative pipeline. The architecture allows you to specify or prompt a layout (which objects should be where) and then the model fills in appearance, context, lighting, and relations coherently. ...

Typeface from Ming Dynasty woodblock printed books. A Ming typeface. Extracted from Ming Dynasty woodblock printed books (凌閔刻本). Using semi-automatic computer vision and OCR. Open-source. A work in progress. Named in honor of 閔齊伋, a 16th-century printer. Intended to be used with Kenyan-lang, the Classical Chinese programming language. Download high-resolution PDFs and split pages into images. Manually lay a grid on top of each page to generate bounding boxes for characters (potentially replaceable by an automatic corner-detection algorithm). ...