Aspose.OCR FOSS

Aspose.OCR FOSS provides open-source libraries for detecting and recognizing text in images and PDF documents. The libraries run entirely offline: text-line detection, region refinement, and Latin-script recognition are performed locally through embedded machine learning models, with no external OCR service and no network call required at runtime. Each recognition result returns both the complete recognized text and line-level bounding boxes, enabling downstream uses such as searchable text overlays, redaction tooling, and recognition-accuracy review. The project is MIT licensed, so developers can use, modify, and redistribute it — including in commercial products — without additional licensing fees. For the enterprise product family, see Aspose.OCR — Enterprise Product Family.