Obsidian plugins with #ocr#

The Omnisearch plugin is a powerful search engine for Obsidian that instantly provides relevant results. Its smart weighting algorithm ensures that the most relevant files are displayed first, making it easy to quickly find notes, documents, PDFs, and images. With features like automatic document scoring, keyboard navigation, and support for quotes and exclusions, Omnisearch is a valuable tool for anyone who needs to quickly locate specific information in their Obsidian vault. Additionally, its workflow is similar to the "Quick Switcher" core plugin, making it easy to integrate into your existing workflow.

The Text Extractor plugin allows you to extract text from images and PDFs within Obsidian, providing a unified way to access this functionality. With support for various file types, including image formats like PNG and JPEG, as well as PDFs and Office documents, this plugin is perfect for those who want to quickly extract information from visual content. The extracted text can be cached for later use, making it easy to access the same information across your devices. While some limitations exist, such as issues with PDF extraction and lack of support on mobile, the Text Extractor plugin remains a valuable tool for anyone looking to streamline their Obsidian experience.

The Image to text OCR plugin allows users to extract text from images within Obsidian. By selecting an image and running a command, the plugin can either replace the image with the recognized text or append the extracted text below the image. It supports various image formats, including .jpg, .jpeg, .png, and more. The plugin offers multiple language recognition options, which can be customized through the settings. It is compatible with both Obsidian and Markdown image formats, providing flexibility for different use cases. Whether for simple note-taking or more advanced document management, this plugin simplifies the process of extracting and displaying text from images.

The MathLive plugin enhances Obsidian's capabilities for handling mathematical content by introducing an intuitive visual editor for creating and editing LaTeX formulas. It renders formulas in real-time, eliminating the need to manually write LaTeX code. The plugin also features an OCR tool that converts scanned images of equations into LaTeX code. This OCR functionality is available in both a cloud-hosted version for efficiency and an open-source option for local use.

The Taskbone plugin enhances productivity in Obsidian by providing tools for seamless integration with Todoist and enabling OCR functionality. It supports two-way synchronization between Obsidian notes and Todoist tasks, with automatic linking in both directions and compatibility with the popular Tasks Obsidian plugin. Users can configure sync options to suit their workflows. The plugin also includes OCR capabilities to extract text from images and format it using customizable templates, making it easy to annotate or insert content directly into notes. These features simplify task management and improve the handling of image-based information within Obsidian.

The Image to notes plugin helps convert handwritten or printed documents into Markdown notes using AI transcription. When you drop image files like JPG, PNG, or HEIC into a specified folder, the plugin processes each one by sending it to an external AI provider and then creates a new note with the transcribed content. It also appends the original image at the bottom of the note for reference. Users can choose from multiple AI providers such as OpenAI, Anthropic, or Google and select a preferred model. There are flexible naming conventions for the resulting notes and options to customise system and user prompts for better transcription output. It's a handy tool for digitising physical notes efficiently, especially for students or professionals handling paper-based material.

The OCR Extractor plugin focuses on turning embedded documents and images into searchable text using optical character recognition. It processes attachments already present in notes and converts the extracted content into clean Markdown, placing it directly below the original file inside a collapsible callout. This approach keeps the raw files untouched while still making their contents visible, searchable, and indexable by both internal search and system-level tools. The plugin supports batch extraction, either for a single note or across the entire vault, with progress shown in the status bar and the option to cancel midway. Text extraction is powered by Mistral OCR, which handles complex layouts better than basic OCR engines.

The Image2LaTEX plugin allows you to convert images of mathematical formulas or content from your clipboard into Markdown or LaTeX format within Obsidian. It supports multiple OCR providers, including self-hosted options like Texify and Pix2Tex, as well as the hosted SimpleTex service. Users can customize their setup by integrating API tokens or local URLs to streamline their workflow. The plugin is ideal for those working with mathematical content, enabling quick and seamless transformations directly into their notes.

The Vision Recall plugin transforms Obsidian into a powerful visual knowledge base by automatically processing and organizing screenshots. It monitors a designated intake folder, instantly capturing and analyzing images using Optical Character Recognition (OCR) and Vision Language Models (LLMs) like OpenAI's GPT-4o or Ollama. Extracted text, AI-generated summaries, and smart tags are added to Obsidian notes for easy retrieval. Users can browse screenshots in a gallery or list view, apply filters, and manage metadata efficiently.

The AI Image OCR plugin enables text extraction from images using modern AI-powered OCR models. It supports both cloud-based providers like OpenAI's GPT-4 family and Google's Gemini series, as well as local models through Ollama or LM Studio. Users can configure where the extracted text should appear-replacing the image embed, inserting at the cursor, or appending to another note. The plugin works with common formats such as PNG and JPG, and offers markdown-formatted output with optional headers, footers, and file naming templates using placeholders. It also allows integration with custom OpenAI-compatible endpoints. For users who prefer not to rely on cloud services, local model support ensures offline capability. This makes the plugin suitable for handling everything from simple printed text to complex handwriting, with flexible output customization to fit different note-taking workflows.

The Student Repo plugin helps students and parents systematically manage study materials, including notes, exam papers, and creative works, by digitizing and organizing them efficiently. It offers AI-powered features like OCR for text extraction, automatic markdown conversion, and intelligent analysis of key topics. The plugin enhances English learning with text-to-speech, translation, grammar analysis, and vocabulary management.

The Image OCR plugin is a game-changer for those who work with images and notes regularly. This plugin allows you to run Optical Character Recognition (OCR) on pasted images, making their contents searchable within Obsidian. With this feature, you can easily find specific information within your images, making it simpler to organize and reference your notes. The plugin also integrates seamlessly with the "Local Images Plus" plugin, ensuring that all your images are stored locally for easy access. Overall, Image OCR is a must-have plugin for anyone who relies heavily on visual content in their Obsidian workflow.

The Handwriting OCR plugin converts handwritten or printed content from images and PDFs into editable text using HandwritingOCR's AI-powered recognition service. It supports a wide range of image formats, multi-page PDFs, and files up to 20MB, making it suitable for digitising notes, archival documents, or scanned material. Extracted text can be copied to the clipboard, appended to an existing note, or saved as a new note, with options accessible via the command palette or right-click menus in both the editor and file explorer. The plugin requires an API key from HandwritingOCR, validates it within the settings, and displays your remaining credits.