Palimpsest: C++ Tool for Extracting Text from Scrolling Screen Recordings

说明与用途

Palimpsest 是一个用于从滚动文档屏幕录像中提取文本的 C++ 工具。它使用“停留门控”技术选择稳定帧，在笔记本电脑上实现了 94.56% 的准确率和 323 FPS 的速度。该工具在本地运行，确保数据隐私。

问题

Extracting text from screen recordings of scrolling documents (e.g., lectures, banking regulations) is difficult because generic OCR tools fail on video, cloud services are expensive and privacy-invasive, and manual transcription is time-consuming. Existing tools do not handle the specific challenge of deduplicating overlapping frames in scrolling content.

结果

Palimpsest successfully extracts text from scrolling screen recordings with 94.56% accuracy on dense banking regulatory text. It achieves 323 FPS on a laptop iGPU by using a lock-free pipeline and 'dwell gating' to process only stable frames, significantly outperforming naive frame-by-frame OCR approaches.

工作流

• Clone the Palimpsest repository from GitHub.
• Run the compile.sh script to build the tool and its dependencies (OpenCV, Tesseract, etc.) via CMake FetchContent.
• Execute the tool on the target video file (e.g., ./build/bin/palimpsest recording.mkv).
• Optionally configure parameters such as --stable-dwell-ms for frame stability, --crop for region of interest, and --ignore for watermark removal.
• Review the generated .txt or .docx output for minor errors.

证据

It runs at 323 FPS on a laptop iGPU and gets 94.56% accuracy on dense banking regulatory text.

来源

From 21,000 frames in a 5 minute 50 second video, only 5 frames were forwarded to OCR in normal operation.

来源