{"id":31105772,"url":"https://github.com/brosgor/criminalfinder","last_synced_at":"2025-09-17T04:06:24.270Z","repository":{"id":314622630,"uuid":"1056192714","full_name":"brosgor/CriminalFinder","owner":"brosgor","description":null,"archived":false,"fork":false,"pushed_at":"2025-09-13T16:17:15.000Z","size":25,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-13T17:47:57.983Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/brosgor.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-13T15:26:43.000Z","updated_at":"2025-09-13T15:42:33.000Z","dependencies_parsed_at":"2025-09-13T17:48:06.937Z","dependency_job_id":"7dc393b7-541d-48f5-9533-aeb293b5dbd2","html_url":"https://github.com/brosgor/CriminalFinder","commit_stats":null,"previous_names":["brosgor/criminalfinder"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/brosgor/CriminalFinder","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brosgor%2FCriminalFinder","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brosgor%2FCriminalFinder/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brosgor%2FCriminalFinder/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brosgor%2FCriminalFinder/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/brosgor","download_url":"https://codeload.github.com/brosgor/CriminalFinder/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brosgor%2FCriminalFinder/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":275531519,"owners_count":25481341,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-17T02:00:09.119Z","response_time":84,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-09-17T04:04:17.425Z","updated_at":"2025-09-17T04:06:24.262Z","avatar_url":"https://github.com/brosgor.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Proyecto de Reconocimiento Facial\n\n## Descripción\nEste proyecto implementa un sistema de reconocimiento facial modular para el curso de Computación Visual (2025-II, profesora Aura María Forero Pachón). Incluye dos módulos principales: uno offline para construir una base de datos de embeddings a partir de imágenes de \"criminales\", y otro en tiempo real para reconocer rostros usando la webcam.\n\n## Requisitos de Sistema\n- Python 3.10+\n- Webcam funcional\n- Sistema operativo: Linux, macOS o Windows\n\n## Instalación\n\n### Crear y activar entorno virtual\n```bash\n# Crear venv\npython -m venv .venv\n\n# Activar venv\n# Linux/macOS:\nsource .venv/bin/activate\n# Windows:\n.\\.venv\\Scripts\\activate\n\n# Instalar dependencias\npip install -r requirements.txt\n```\n\n### Notas de Instalación para face_recognition/dlib\nLa biblioteca `face_recognition` depende de `dlib`, que requiere compilación. En algunos sistemas, puede necesitar dependencias adicionales:\n\n- **Ubuntu/Debian**: `sudo apt-get install build-essential cmake libgtk-3-dev libboost-all-dev`\n- **macOS**: Instalar Xcode Command Line Tools\n- **Windows**: Instalar Visual Studio Build Tools\n\nSi `face_recognition` no se instala correctamente, el proyecto incluye un fallback básico usando OpenCV, pero con menor precisión.\n\nDocumentación oficial: [face_recognition](https://github.com/ageitgey/face_recognition) y [dlib](http://dlib.net/)\n\n## Uso\n\n### 1. Preparar imágenes\nColoca imágenes de personas en el directorio `criminales/`. Puedes usar:\n- Archivos individuales: `criminales/Juan_Perez.jpg`\n- Carpetas por persona: `criminales/Juan_Perez/1.jpg`, `criminales/Juan_Perez/2.jpg`\n\n### 2. Construir base de embeddings\n```bash\npython main.py offline --input criminales --output embeddings_criminales.pkl --model hog\n```\n\n### 3. Ejecutar reconocimiento en tiempo real\n```bash\npython main.py realtime --db embeddings_criminales.pkl --threshold 0.6 --detector hog --camera 0\n```\n\n## Parámetros Recomendados\n- `scale`: 0.25 para buen rendimiento en CPU\n- `detector`: \"hog\" para CPU, \"cnn\" si tienes GPU compatible con CUDA\n- `threshold`: 0.6 por defecto, ajustar según necesidades (menor valor = más estricto)\n\n## Métricas Esperadas\n- ≥15 FPS en CPU moderna con scale=0.25\n- Precisión depende de la calidad de las imágenes de referencia\n\n## Ética y Privacidad\nEste proyecto es únicamente para fines académicos. Los datos se procesan localmente sin enviar información a servicios externos.\n\n## Troubleshooting\n- **No detecta cámara**: Verificar que la webcam esté conectada y no en uso por otra aplicación\n- **Error instalando dlib**: Seguir las instrucciones de compilación específicas del sistema\n- **Cero rostros detectados**: Verificar iluminación y calidad de imágenes\n- **Tuning de threshold**: Probar valores entre 0.4-0.8 según el caso de uso\n\n## Estructura del Proyecto\n```\nproyecto_reconocimiento/\n├── main.py                 # Punto de entrada\n├── modulos/\n│   ├── procesamiento.py    # Módulo offline\n│   └── deteccion.py        # Módulo tiempo real\n├── criminales/             # Imágenes de referencia\n├── embeddings_criminales.pkl # Base de datos generada\n├── requirements.txt        # Dependencias\n└── README.md               # Este archivo\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrosgor%2Fcriminalfinder","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbrosgor%2Fcriminalfinder","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrosgor%2Fcriminalfinder/lists"}