Metadata-Version: 2.4
Name: nilparadox-imageai
Version: 0.1.0
Summary: Explainable, physics-based image forensics (AI enhancement, screenshots, resampling) with structured decisions.
Author: Nilanjan Panda
License: MIT
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: numpy>=1.23
Requires-Dist: pillow>=10.0
Requires-Dist: typer>=0.9
Requires-Dist: rich>=13.0
Requires-Dist: scipy>=1.9
Requires-Dist: pillow-heif>=0.16.0

# imageai

Explainable, physics-based image forensics for:
- camera computational enhancement (denoise / sharpen / beautify)
- screenshots
- resampling artifacts

No end-to-end deep learning classifier. Outputs structured decisions.

## Install (local)
pip install -e .

## CLI
imageai detect /path/to/image.jpg

## Python API
from imageai.api import detect_image
result = detect_image("/path/to/image.jpg")
print(result)

