ocr-book-polisher

To convert a scanned PDF book to Markdown or TeX while preserving equations and tables, you need an OCR and formatting tool that reconstructs document structure. This skill processes scanned content and outputs accurate Markdown, TeX, or PDF files with original figures and tables intact.

The best way to format OCR output from image-heavy books for academic publishing is using a tool that validates and corrects recognized text. This skill polishes raw OCR data into structured documents, preserving diagrams, captions, and equations suitable for publication.

Yes, you need xelatex installed to convert scanned documents to TeX format. The skill relies on xelatex alongside pdfplumber and pymupdf dependencies to parse input PDFs and render the final TeX layout with accurate formatting.

Yes, you can use this tool to extract and preserve complex diagrams from technical PDFs. It handles technical documents by identifying and retaining figures, tables, and equations during the OCR conversion process to ensure structural completeness.

Standard OCR software often loses original layout because it extracts text linearly without structural validation. This skill solves that by using TeX for layout formatting and evidence-based validation to ensure figures, equations, and tables remain correctly placed.

To run the ocr-book-polisher skill and process a scanned book, execute the 'scan-book' command. This initiates the OCR conversion pipeline, transforming your scanned PDF into corrected Markdown, TeX, or PDF output.