Update app.py

app.py

@@ -96,37 +96,48 @@ def estimar_probabilidad_manipulacion(porcentaje_ela):
     else:
         return "Muy alta (> 15%) - Manipulación extensa o generación por IA detectada."
 
+
 def realizar_ela(imagen):
     try:
         img_np = np.array(imagen.convert("RGB"))
         img_cv = cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
 
-        quality = 95
-        noise_level = 18
-        error_scale = 57
+        quality = 90
+        noise_level = 8
+        error_scale = 25
+        brightness_pct = 100
+        equalize_histogram = False
 
         temp_path = "/tmp/temp_image.jpg"
         cv2.imwrite(temp_path, img_cv, [cv2.IMWRITE_JPEG_QUALITY, quality])
         img_comprimida = cv2.imread(temp_path)
-        
         if img_comprimida is None:
             raise ValueError("No se pudo leer la imagen comprimida.")
 
         diferencia = cv2.absdiff(img_cv.astype(np.float32), img_comprimida.astype(np.float32))
-        scaled_diff = diferencia * (noise_level / 10.0) * (error_scale / 10.0)
+        scaled_diff = diferencia * (noise_level / 10.0) * (error_scale / 100.0) * 20.0
         scaled_diff = np.clip(scaled_diff, 0, 255).astype(np.uint8)
 
         gray_diff = cv2.cvtColor(scaled_diff, cv2.COLOR_BGR2GRAY)
-        _, mask = cv2.threshold(gray_diff, 10, 255, cv2.THRESH_BINARY)
-        
-        result = scaled_diff.copy()
-        mask_colored = cv2.merge([mask, mask, np.zeros_like(mask)])
-        background = cv2.addWeighted(img_cv, 0.3, np.zeros_like(img_cv), 0.7, 0)
-        result = np.where(mask[:, :, None] > 0, mask_colored, background)
-        result = cv2.convertScaleAbs(result, alpha=1.2, beta=10)
-
-        if os.path.exists(temp_path):
-            os.remove(temp_path)
+        _, mask = cv2.threshold(gray_diff, 20, 255, cv2.THRESH_BINARY)
+        mask = mask.astype(np.uint8)
+
+        if equalize_histogram:
+            gray = cv2.cvtColor(scaled_diff, cv2.COLOR_BGR2GRAY)
+            gray_eq = cv2.equalizeHist(gray)
+            scaled_diff = cv2.cvtColor(gray_eq, cv2.COLOR_GRAY2BGR)
+
+        brightness_factor = min(1.1, brightness_pct / 100.0)
+        scaled_diff = cv2.convertScaleAbs(scaled_diff, alpha=brightness_factor, beta=0)
+
+        ela_color = scaled_diff.copy()
+        img_gray = cv2.cvtColor(img_cv, cv2.COLOR_BGR2GRAY)
+        img_gray = cv2.cvtColor(img_gray, cv2.COLOR_GRAY2BGR)
+        img_gray = cv2.convertScaleAbs(img_gray, alpha=0.5, beta=0)
+
+        result = np.where(mask[..., None] > 0, ela_color, img_gray)
+
+        os.remove(temp_path)
         return result, mask
 
     except Exception as e:
@@ -135,6 +146,9 @@ def realizar_ela(imagen):
         cv2.putText(error_img, "ERROR AL PROCESAR ELA", (50, 150), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2)
         return error_img, None
 
+
+
+
 def crear_graficos_estadisticas(porcentaje_ela, dimensiones, metadatos):
     """Crear gráficos estadísticos para el análisis ELA"""