# cristian-bejarano/contando-dedos architecture

> Architecture diagram of the GitHub repository cristian-bejarano/contando-dedos, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-20). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/cristian-bejarano/contando-dedos
- Repository: https://github.com/cristian-bejarano/contando-dedos

## Overview

Lengua de Señas Colombiana is a webcam-based sign-letter recognition prototype. The documented path is to capture labeled hand-motion samples, train a classifier, and recognize signs live or in a guided practice mode; evaluation scripts compare model performance. The excerpts show capture and recognition using MediaPipe landmarks, normalization, and persisted Random Forest artifacts. The README mentions a menu entry point that is absent from the tree, so it is not mapped; evaluation-script relationships are shown only where source explicitly supports them.

Main entry points: [`abcedario/reconocer_libre.py`](https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/reconocer_libre.py) (Live recognition), [`abcedario/reconocer_practica.py`](https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/reconocer_practica.py) (Practice recognition), [`abcedario/capturar.py`](https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/capturar.py) (Capture samples), [`abcedario/datos`](https://github.com/cristian-bejarano/contando-dedos/tree/main/abcedario/datos) (Labeled landmarks)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Sample collection"]
  node_capture["Capture samples<br/>[capturar.py]"]
  node_samples[("Labeled landmarks")]
end

subgraph group_model["Model lifecycle"]
  node_train["Train classifier<br/>[entrenar.py]"]
  node_artifacts[("Model artifacts")]
  node_evaluate["Evaluate classifier<br/>[evaluar.py]"]
  node_inference_eval["Repeated CV analysis<br/>[inferencia.py]"]
  node_reports["Evaluation reports"]
end

subgraph group_recognition["Recognition experience"]
  node_live["Live recognition<br/>[reconocer_libre.py]"]
  node_practice["Practice recognition"]
end

subgraph group_runtime["Vision runtime"]
  node_landmarker["Hand landmarker"]
  node_mediapipe_demo["Landmark demo"]
end

node_signer(("Signer"))
node_webcam["Webcam"]

node_signer -->|"performs signs"| node_capture
node_webcam -->|"supplies frames"| node_capture
node_capture -->|"writes samples"| node_samples
node_samples -->|"loads samples"| node_train
node_train -->|"saves model"| node_artifacts
node_artifacts -->|"loads model"| node_live
node_artifacts -->|"loads model"| node_practice
node_webcam -->|"supplies frames"| node_live
node_webcam -->|"supplies frames"| node_practice
node_live -->|"shows letter"| node_signer
node_practice -->|"shows letter"| node_signer
node_evaluate -->|"loads samples"| node_samples
node_evaluate -->|"writes reports"| node_reports
node_inference_eval -->|"loads samples"| node_samples
node_inference_eval -->|"writes distributions"| node_reports
node_capture -->|"configures"| node_landmarker
node_live -->|"configures"| node_landmarker
node_practice -->|"configures"| node_landmarker
node_mediapipe_demo -->|"configures"| node_landmarker
node_signer -.->|"uses mode"| node_live
node_signer -.->|"uses mode"| node_practice

click node_capture "https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/capturar.py"
click node_samples "https://github.com/cristian-bejarano/contando-dedos/tree/main/abcedario/datos"
click node_train "https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/entrenar.py"
click node_artifacts "https://github.com/cristian-bejarano/contando-dedos/tree/main/abcedario/moldes"
click node_evaluate "https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/evaluar.py"
click node_inference_eval "https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/inferencia.py"
click node_reports "https://github.com/cristian-bejarano/contando-dedos/tree/main/abcedario/evaluaciones"
click node_live "https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/reconocer_libre.py"
click node_practice "https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/reconocer_practica.py"
click node_landmarker "https://github.com/cristian-bejarano/contando-dedos/blob/main/modelos/hand_landmarker.task"
click node_mediapipe_demo "https://github.com/cristian-bejarano/contando-dedos/blob/main/prueba_mediapipe.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_capture,node_samples toneBlue
class node_train,node_artifacts,node_evaluate,node_inference_eval,node_reports toneAmber
class node_live,node_practice toneMint
class node_landmarker,node_mediapipe_demo toneRose
class node_signer,node_webcam toneIndigo
```

## Components

### Sample collection

- [Capture samples](https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/capturar.py): `abcedario/capturar.py`
- [Labeled landmarks](https://github.com/cristian-bejarano/contando-dedos/tree/main/abcedario/datos): `abcedario/datos`

### Model lifecycle

- [Train classifier](https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/entrenar.py): `abcedario/entrenar.py`
- [Model artifacts](https://github.com/cristian-bejarano/contando-dedos/tree/main/abcedario/moldes): `abcedario/moldes`
- [Evaluate classifier](https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/evaluar.py): `abcedario/evaluar.py`
- [Repeated CV analysis](https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/inferencia.py): `abcedario/inferencia.py`
- [Evaluation reports](https://github.com/cristian-bejarano/contando-dedos/tree/main/abcedario/evaluaciones): `abcedario/evaluaciones`

### Recognition experience

- [Live recognition](https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/reconocer_libre.py): `abcedario/reconocer_libre.py`
- [Practice recognition](https://github.com/cristian-bejarano/contando-dedos/blob/main/abcedario/reconocer_practica.py): `abcedario/reconocer_practica.py`

### Vision runtime

- [Hand landmarker](https://github.com/cristian-bejarano/contando-dedos/blob/main/modelos/hand_landmarker.task): `modelos/hand_landmarker.task`
- [Landmark demo](https://github.com/cristian-bejarano/contando-dedos/blob/main/prueba_mediapipe.py): `prueba_mediapipe.py`

### Other components

- **Signer**
- **Webcam**

## Connections

- Signer → Capture samples: performs signs (evidence: `README.md`)
- Webcam → Capture samples: supplies frames (evidence: `abcedario/capturar.py`)
- Capture samples → Labeled landmarks: writes samples (evidence: `abcedario/capturar.py`)
- Labeled landmarks → Train classifier: loads samples (evidence: `abcedario/entrenar.py`)
- Train classifier → Model artifacts: saves model (evidence: `abcedario/entrenar.py`)
- Model artifacts → Live recognition: loads model (evidence: `abcedario/reconocer_libre.py`)
- Model artifacts → Practice recognition: loads model (evidence: `abcedario/reconocer_practica.py`)
- Webcam → Live recognition: supplies frames (evidence: `abcedario/reconocer_libre.py`)
- Webcam → Practice recognition: supplies frames (evidence: `abcedario/reconocer_practica.py`)
- Live recognition → Signer: shows letter (evidence: `abcedario/reconocer_libre.py`)
- Practice recognition → Signer: shows letter (evidence: `abcedario/reconocer_practica.py`)
- Evaluate classifier → Labeled landmarks: loads samples (evidence: `abcedario/evaluar.py`)
- Evaluate classifier → Evaluation reports: writes reports (evidence: `abcedario/evaluar.py`)
- Repeated CV analysis → Labeled landmarks: loads samples (evidence: `abcedario/inferencia.py`)
- Repeated CV analysis → Evaluation reports: writes distributions (evidence: `abcedario/inferencia.py`)
- Capture samples → Hand landmarker: configures (evidence: `abcedario/capturar.py`)
- Live recognition → Hand landmarker: configures (evidence: `abcedario/reconocer_libre.py`)
- Practice recognition → Hand landmarker: configures (evidence: `abcedario/reconocer_practica.py`)
- Landmark demo → Hand landmarker: configures (evidence: `prueba_mediapipe.py`)
- Signer → Live recognition: uses mode (evidence: `README.md`)
- Signer → Practice recognition: uses mode (evidence: `README.md`)
