Small application for Vietnamese scenetext detection and recognition
Play-ParSeq is a Play module which seamlessly integrates ParSeq with Play Framework
OCR in pure Rust: documents, screens, and a change-gated LIVE frame reader. Detection, recognition and reading order computed from geometry, no Python, no C/C++ by default, nothing GPL. Memory safe. The ffai-carmenta crate.
An end-to-end computer vision pipeline for weather-invariant OCR, combining Restormer-based deraining, CRAFT text detection, and PARSeq recognition for edge and web deployment.
Fine-tuning pipeline for the PARSeq scene text recognition model on your own labeled text crops.
To associate your repository with the parseq topic, visit your repo's landing page and select "manage topics."