Local-first Python toolkit for image archive analysis, OCR, metadata extraction, duplicate detection, folder audits, and HTML gallery review.
This repository is currently being prepared as a public-safe portfolio version.
The original workflow was developed as a local-first image archive analysis system. This public version is being organized step by step with sanitized examples, beginner-readable documentation, and code that can be reviewed or replicated without exposing private files, personal archives, client data, or sensitive metadata.
Last updated: May 23, 2026.
Visual Archive Intelligence Suite is a practical local workflow prototype for organizing, reviewing, and analyzing large image collections.
The project is designed for people who need to understand what is inside large visual archives without uploading private files to cloud services.
This repository is part of my applied AI and workflow-design portfolio. It demonstrates:
- Local-first automation
- Python scripting for practical workflow problems
- OCR-assisted image review
- Metadata and EXIF inspection
- Duplicate and near-duplicate detection concepts
- Image dimensions and orientation analysis
- Folder and file-path auditing
- HTML gallery/report generation
- Human-in-the-loop review design
- Privacy-aware technical architecture
The public version is being prepared with sanitized demo data and simplified scripts.
Planned modules:
- Image inventory scanner
- File metadata extractor
- OCR text extraction workflow
- Duplicate detection using hashes
- Image size and orientation report
- HTML gallery generator
- Folder audit report
- Demo dataset and sample output
This project is intended to run locally.
No private image archive, personal dataset, client data, real user files, or sensitive metadata is included in this repository.
Public examples will use small demo files only.
Status: public-safe repository in preparation.
Current stage:
- Repository created
- README prepared
- Public-safe structure being organized
- Demo files and sample outputs planned
visual-archive-intelligence-suite/
├── README.md
├── LICENSE
├── requirements.txt
├── src/
│ ├── scan_images.py
│ ├── extract_metadata.py
│ ├── detect_duplicates.py
│ ├── generate_gallery.py
│ └── utils.py
├── docs/
│ ├── privacy-first-design.md
│ ├── features.md
│ └── roadmap.md
├── sample_data/
├── sample_output/
└── screenshots/