Idea Notes vs FrankenOCR

APP INTERFACE: English. IdeaCatch is a focused, private notebook for thoughts that arrive before you have time to organize them. CAPTURE FIRST - Save a thought in a few taps - Type @work, @app, @blog, @biz or @personal anywhere in the line to file it automatically - Edit, delete or favorite any saved idea FIND IT AGAIN - Search both idea text and tag names - Filter the notebook by tag - Group by tag or sort alphabetically - Export every saved idea as Markdown or CSV FULL ACCESS Full Access removes the saved-idea cap and unlocks custom @tags. Weekly, yearly and one-time lifetime options may be available. Prices, billing periods and availability are supplied by Apple. An introductory offer appears only when the App Store reports both an offer and eligibility for your Apple Account. Saved ideas always remain readable, editable, exportable and deletable. PRIVATE BY DESIGN Ideas stay in the app's on-device database. There is no account, advertising or analytics SDK, and IdeaCatch does not collect or sell personal data. Optional daily reminders are scheduled locally by iOS, and notification permission is requested only when you enable one. Terms of Use: https://leanstudio.asia/terms-of-use Privacy Policy: https://leanstudio.asia/privacy-policy Support: support@leanstudio.asia

Extract text from an image or scanned PDF without uploading the document. FrankenOCR uses the same pure-Rust Unlimited-OCR engine as the FrankenOCR command-line project. Choose a photo, file, camera capture, tall scrolling screenshot, or scanned PDF. The app reads the input in memory and produces structured Markdown on the device. The flagship recognition path uses a downloaded, verified Baidu Unlimited-OCR model for careful document extraction. Tall screenshots are divided with overlap-aware smart cuts, while PDF pages are processed as a document and low-yield pages are called out instead of silently disappearing. Live Camera mode uses Apple's on-device Vision text recognition for speed. It is less accurate than the flagship FrankenOCR model, and the app labels that tradeoff clearly. Recognized words flow from their camera positions into the capture tray as the view updates. The current app ships one flagship model: Unlimited-OCR. It does not claim to include GOT-OCR2, SmolVLM2, OneChart, or a music-recognition model. Images, PDFs, camera frames, and recognized text stay on the device. Network access is used only to download the static flagship model files.