OCR Vision Renamer

Python utility for proposing safe image filenames from OCR-detected text and vision-model captions.

This is a curated public portfolio copy of the OCR_Vision_Renamer project. It includes the application source and runnable scripts, without local IDE state, scratch images, logs, or generated test output.

Features

• Tkinter GUI with preview workflow before applying renames.
• Optional image preview during review.
• Filename sanitization for Windows path constraints.
• JSONL rename logging for auditability.
• Optional folder watcher for camera-upload workflows.
• OpenAI vision fallback when local OCR does not provide useful text.

Requirements

Python dependencies are listed in requirements.txt.

Vision features use the OPENAI_API_KEY environment variable. Local OCR depends on pytesseract and a working Tesseract installation.

Example

python scripts/run_gui.py

or:

python scripts/batch_cli.py --help

Validation

The Python files in this public copy were syntax-checked with python -m py_compile.