<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>PDF OCR on Architect PARK JUN WOO</title><link>https://www.parkjunwoo.com/tags/pdf-ocr/</link><description>Recent content in PDF OCR on Architect PARK JUN WOO</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 10 Jul 2026 20:00:00 +0900</lastBuildDate><atom:link href="https://www.parkjunwoo.com/tags/pdf-ocr/index.xml" rel="self" type="application/rss+xml"/><item><title>Installing and Using MarkItDown — Why Image-Only PDFs Fail, and How to Bolt On OCR</title><link>https://www.parkjunwoo.com/tech/markitdown-install-and-ocr-setup/</link><pubDate>Fri, 10 Jul 2026 15:00:00 +0900</pubDate><guid>https://www.parkjunwoo.com/tech/markitdown-install-and-ocr-setup/</guid><description>The reason to use MarkItDown comes down to the agent-operable condition — Microsoft&amp;rsquo;s own conversion of its own formats is structurally trustworthy. Installation, usage, and how to bolt on OCR at the exact point that trust breaks: image-only PDFs.</description></item></channel></rss>