Bỏ qua đến nội dung

Auto Image Occlusion

Chờ xử lý #anki #addon #auto #image #occlusion
https://github.com/BEST8OY/Auto-Occlusion-Anki-Addon
20/10/2025

Cách tải addon Auto Image Occlusion

Bạn có thể tải addon bằng một trong hai cách sau:

Click nút Copy bên dưới để copy code vào clipboard

1414192727

Sau đó mở Anki → Tools → Add-ons → Get Add-ons → Dán code → OK

Mở trang addon trên AnkiWeb và tìm mã code ở cuối trang

Mở trên AnkiWeb

Cuộn xuống cuối trang AnkiWeb, tìm dòng có mã code 1414192727 và copy

1

Mô tả chi tiết

Auto Image Occlusion — Automatic Image Occlusion for Anki

Automatically detect text regions in images and create Image Occlusion shapes with a single click. Ideal for diagrams, anatomy labels, flowcharts and other images with scattered or multi-line labels.

Key features One-click auto-detection of text regions powered by Tesseract OCR (PSM 12 — sparse text with OSD) Line-based grouping and vertical merging to handle multi-line labels reliably Configurable filters: confidence threshold, minimum size, area percentage, and merge factor Collision detection to avoid duplicating existing occlusions Works with Anki’s native Image Occlusion UI Quick highlights Fast and reliable for diagrams and documents Tunable for noisy, low-quality, or high-density images Integrates with Anki’s Image Occlusion toolbar and supports a keyboard shortcut (Ctrl+Shift+A) Requirements Anki 25.09+ (Image Occlusion available) Tesseract OCR installed on your system Quick install

Install Tesseract on your OS:

Debian/Ubuntu: sudo apt-get install tesseract-ocr

macOS: brew install tesseract

Windows: download and install from UB Mannheim or official release pages

Install this addon in Anki.

Configuration (examples)

Default config (works for most):

{ “tesseract_lang”: “eng”, “min_confidence”: 48, “vertical_merge_factor”: 0.65 }

More detections (blurry images):

{ “min_confidence”: 35, “min_area_percent”: 0.00005 }

Fewer false positives (high-quality images):

{ “min_confidence”: 60, “min_area_percent”: 0.001 }

How it works (short) Captures image from the Image Occlusion editor. Sends image to Python backend → Tesseract OCR (PSM 12, sparse text with OSD). Groups words by line, filters by confidence/size/length, merges vertically adjacent lines. Returns occlusion boxes to the editor for review and fine-tuning. Troubleshooting tips If nothing is detected, check Tesseract installation and lower min_confidence / min_area_percent. For timeouts, reduce image resolution (~1920px width) or increase JavaScript timeout. If you see pytesseract.TesseractNotFoundError, ensure Tesseract is in PATH.

For full documentation, configuration details, screenshots, and the source code — visit the project on GitHub: https://github.com/BEST8OY/Auto-Image-Occlusion-Anki-Addon


Liên kết hỗ trợ


Reviews (1)

👍 2025-10-26

Works brilliantly. Just need some intelligence to read and follow the instructions :) Thank you so much for saving me a lot of time and effort.