up

.gitignore

@@ -1 +1,2 @@
 .venv/
+__pycache__/

Dockerfile

@@ -1,15 +1,12 @@
-# Usa una imagen base de Python
 FROM python:3.12.7
-# Establece el directorio de trabajo
+
 WORKDIR /code
 
-# Copia los archivos necesarios al contenedor
 COPY ./requirements.txt /code/requirements.txt
 RUN pip install --no-cache-dir -r /code/requirements.txt
 RUN pip install fastapi uvicorn
 
 COPY . .
-
 RUN chmod -R 777 /code
 
 # Comando para ejecutar la aplicación

app.py

@@ -1,33 +1,66 @@
-from fastapi import FastAPI, File, UploadFile, HTTPException, Query
-from fastapi.responses import HTMLResponse
-from pydantic import BaseModel
-from typing import List
+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.responses import JSONResponse
+from typing import List, Dict
 import cv2
 from PIL import Image
 import numpy as np
 from io import BytesIO
+import base64
 
 app = FastAPI()
 
-def buscar_existe(image):
-    existe = "NO"
-    print("resultado: ", image.shape)
-    eyeglasses_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml') 
+
+def detect_eyes(image: np.ndarray) -> List[Dict[str, str]]:
+    eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml')
     gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
-    eyeglasses = eyeglasses_cascade.detectMultiScale(gray, 1.3, 5, minSize=(10, 10))
-    for (x, y, w, h) in eyeglasses:
-        existe = "SI"
-        break
+    eyes = eye_cascade.detectMultiScale(gray,
+                                        scaleFactor=1.1,
+                                        minNeighbors=5,
+                                        minSize=(30, 30)
+                                        )
+    print("Detected eyes:", eyes, type(eyes))
+    if len(eyes) == 0:
+        return []
+    detections = []
+    for (x, y, w, h) in eyes:
+        # para dibujar rectangulos en ojos detectados
+        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
+
+        detections.append({
+            "label": "eye",
+            "bounding_box": {
+                "x": int(x),
+                "y": int(y),
+                "width": int(w),
+                "height": int(h)
+            }
+        })
+    return detections
 
-    return existe
 
-# Ruta de predicción
 @app.post('/predict/')
-async def predict(file: UploadFile = File(...), rostro: str = Query(...)):
+async def predict(file: UploadFile = File(...)) -> JSONResponse:
     try:
-        image = Image.open(BytesIO(await file.read()))
-        image = np.asarray(image)
-        prediction = buscar_existe(image)
-        return {"prediction": prediction}
+        image = Image.open(BytesIO(await file.read())).convert("RGB")
+        image_np = np.array(image)
+
+        detections = detect_eyes(image_np)
+        if len(detections) == 0:
+            return JSONResponse(content={
+                "detections": detections,
+                "count": 0,
+                "image_with_detections": None
+            })
+
+        _, buffer = cv2.imencode('.jpg', image_np)
+        image_base64 = base64.b64encode(buffer).decode('utf-8')
+
+        return JSONResponse(content={
+            "detections": detections,
+            "count": len(detections),
+            "image_with_detections": image_base64
+        })
     except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
+        raise HTTPException(
+            status_code=500,
+            detail=f"Error al procesar la imagen: {str(e)}")

requirements.txt

@@ -1,4 +1,4 @@
-fastapi[standard]
+fastapi[stardard]
 numpy
 pydantic
 opencv-python-headless