https://github.com/swish78/photosorter
Automatically group similar images using computer vision techniques.
https://github.com/swish78/photosorter
Last synced: over 1 year ago
JSON representation
Automatically group similar images using computer vision techniques.
- Host: GitHub
- URL: https://github.com/swish78/photosorter
- Owner: Swish78
- License: mit
- Created: 2025-03-26T07:37:30.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-26T20:50:01.000Z (over 1 year ago)
- Last Synced: 2025-03-26T21:32:52.952Z (over 1 year ago)
- Language: Python
- Homepage:
- Size: 25.4 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# PhotoSorter
Automatically group similar images using computer vision techniques.
## Installation
```bash
pip install photosorter
```
## Usage
After installation, you can use the `photosorter` command directly from your terminal:
```bash
photosorter [sift|deeplearning] SOURCE DESTINATION [-t THRESHOLD] [-l LIMIT] [-v]
```
### Arguments
- `method`: Similarity detection method (sift/deeplearning)
- `source`: Source directory containing images
- `destination`: Output directory for grouped images
### Options
- `-t, --threshold`: Similarity threshold (0.0-1.0)
- `-l, --limit`: Maximum number of images to process
- `-v, --verbose`: Enable detailed processing output
## Methods
1. **SIFT** - Traditional feature matching using Scale-Invariant Feature Transform
2. **DeepLearning** - ResNet-50 embeddings with cosine similarity comparison
## Example
```bash
# Using deep learning method with 0.8 similarity threshold
photosorter deeplearning ./photos ./sorted_images -t 0.8
```