ImageXtract: Private PDF OCR

Extract Text, Tables & Figures

Only for Mac

$4.99

Mac

Turn any folder into an automated OCR inbox. ImageXtract processes images and PDFs on-device and creates Markdown files beside the originals. Turn PDFs and images into structured, searchable and exportable content—privately on your Mac. ImageXtract is a native macOS OCR workspace for extracting content from documents, scans, screenshots and clipboard images. It preserves page structure, identifies different kinds of content, and keeps your projects, search index and results available between launches. Recognition and search run locally. Your imported documents and extracted content remain on your Mac. EXTRACT STRUCTURED CONTENT ImageXtract recognizes more than plain lines of text. It identifies regions such as: • Titles and headings • Paragraphs and lists • Tables • Captions • Images and figures Open a completed page to review the source and extracted content side by side. Color-coded bounding boxes show where each result came from, while synchronized highlighting connects the page with its extracted regions. Copy text regions with one click, preview detected figures at full resolution, or copy image crops directly to the clipboard. WORK WITH PDFS AND IMAGES Import content using: • File selection • Drag and drop • The clipboard ImageXtract supports common image formats including JPEG, PNG, WebP, TIFF, BMP, GIF, AVIF and HEIC, as well as multi-page PDF documents. For PDFs, choose individual pages or enter ranges such as 1-4, 7, 9-12. Processing begins incrementally as pages are prepared, so you do not need to wait for an entire document before extraction starts. ORGANIZE EVERYTHING INTO PROJECTS Create projects for research, notes, reports, archives or any other collection of related material. Each project provides: • Persistent document organization • Filtering by type and processing status • Sorting by name, status or recency • Project-specific extraction profiles • Search across all completed content • Project-wide export For occasional tasks, Quick Extract lets you process content without first creating a project. SEARCH INSIDE YOUR DOCUMENTS Search across an entire project or within a selected PDF. ImageXtract supports phrases, alternatives, exclusions and filters for regions, documents and page numbers. Search results include highlighted excerpts and take you directly to the matching page and detected region. Example searches include: • "annual revenue" • invoice OR receipt • invoice -draft • label:table • document:report page:12 The search index is stored and queried locally. EXPORT IN THE FORMAT YOU NEED Export individual pages, complete PDFs or entire projects. Available formats include: • Markdown • JSON • Spatial text • Spatial HTML • Microsoft Word documents Exports can retain region order, labels, coordinates, tables, layout and detected image crops, depending on the selected format. Markdown exports can link to extracted figures. JSON includes labels and normalized coordinates. Spatial text approximates the original page arrangement. HTML preserves positioned content, tables and images. Word export produces multi-page documents with embedded tables and figures. BUILT FOR LARGE DOCUMENT COLLECTIONS ImageXtract is designed to stay responsive as your workspace grows. Projects, documents, PDF pages and search results are loaded incrementally rather than all at once. Processing state is saved between launches. Interrupted items can recover when the app reopens, and the extraction queue can be paused or resumed after the current page. PRIVATE BY DESIGN ImageXtract uses a bundled, locally stored OCR model optimized for Apple Silicon and dynamically quantized to 4-bit for a balance of quality, speed and memory efficiency. The OCR engine runs with less than 2 GB of RAM. Recognition, document storage and full-text search operate on local files. No cloud processing is required. Your source documents, extracted content, search indexes and exports remain on your Mac. SYSTEM REQUIREMENTS • Apple Silicon Mac • macOS 15.5 or later • Sufficient storage for the local OCR model, imported documents, rendered PDF pages and exports

Ratings & Reviews

  • This app hasn’t received enough ratings or reviews to display an overview.

### What’s New in Version 1.2.0 Introducing **Observe & Extract**: - Link a folder to automatically process new and existing images and PDFs. - Monitor nested folders while ImageXtract is running. - Create searchable Markdown files beside the original documents. - Pause, resume, retry, disconnect, or reauthorize folder access at any time. - Safely preserve source files and report conflicts without overwriting existing Markdown. This release also improves extraction recovery, PDF processing, and overall reliability.

Version 1.2.0

The developer, Mauro Sciancalepore, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy .

  • Data Not Collected

    The developer does not collect any data from this app.

    Privacy practices may vary, for example, based on the features you use or your age. Learn More

    Accessibility

    The developer has not yet indicated which accessibility features this app supports. Learn More

    Information

    Seller
    • Mauro Sciancalepore
    Size
    • 1.7 GB
    Category
    • Productivity
    Compatibility
    Requires macOS 15.5 or later and a Mac with Apple M1 chip or later.
    • Mac
      Requires macOS 15.5 or later and a Mac with Apple M1 chip or later.
    Languages
    • English
    Age Rating
    4+
    Copyright
    • © 2026 Mauro Sciancalepore
  • Privacy Policy

    • Supports

    • Family Sharing

      Up to six family members can use this app with Family Sharing enabled.