Obsidian plugins with #image-processing#

The Image Converter plugin handles image conversion, compression, resizing and annotation inside the vault. It converts dropped or pasted images to WEBP, JPG or PNG, supports WEBP, JPG, PNG, HEIC and TIF, and lets you control compression with a quality value from 1 to 100. Resizing works on linked dimensions and on the original file, with drag, scrollwheel and size modes such as longest edge, shortest edge, fit and fill. It also adds alignment, text wrapping, crop, rotate and flip tools, plus in app markup for drawing, writing and scribbling on images. File handling is configurable through variable based renaming, custom output folders, batch processing, markdown image links, wiki links and right click actions including Base64 copy and vault deletion.

The Inkporter plugin streamlines the process of digitizing handwritten notes in Obsidian by intelligently isolating ink from scans and optimizing them for digital use. It automates tasks such as ink isolation, grayscale conversion, and adaptive theming while offering real-time previews. The plugin supports direct clipboard imports, smart file naming, and seamless integration with Obsidian's CSS theming for a polished appearance. Users can fine-tune ink detection settings for optimal contrast and clarity, ensuring clean and readable scans.

The AI Image Analyser plugin sends image files to an Ollama model and stores the returned keywords inside your vault for later reuse. It works with JPG, JPEG, PNG and WebP images, and lets you trigger analysis from the context menu or command palette. The default setup uses llava-llama3, though the model can be switched to llava, llava:13b or llava:34b in settings. Results are cached in a JSON file inside the plugin folder, which means repeated analysis is avoided and cached data can be synced across devices. It also connects with OmniSearch, so image analysis results can be indexed and searched when its indexing option is enabled.

The Latex OCR plugin allows Obsidian users to convert images of equations into editable LaTeX code within their vault. By leveraging either the HuggingFace API or a locally-run model, the plugin can generate LaTeX equations from clipboard images or existing image files through contextual commands. Users can configure the plugin to suit their workflow, including enabling local processing for enhanced control. This tool is particularly useful for academic, technical, and scientific note-taking, offering a streamlined way to incorporate precise mathematical and technical content into Obsidian 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 Scan Sketch plugin turns photos of notebook pages and loose documents into cleaner images you can drop into your notes. It can pull an image from a file picker or the camera, detect page corners, straighten perspective, rotate the shot and let you fine tune the crop by dragging four points. It also includes brightness, contrast, saturation and black and white controls, plus background removal with live preview before export. You can save the result as PNG, JPG or SVG, pick from multiple destination folders and insert the embed link into the active note at the cursor.