diff --git a/datasets/raise/extract_noise.py b/datasets/raise/extract_noise.py
index c494edb..2dfb0aa 100755
--- a/datasets/raise/extract_noise.py
+++ b/datasets/raise/extract_noise.py
@@ -75,7 +75,7 @@ def treatImage(imageFileName, computeExtremes = False, color = None):
     if denoiser != 'mean':
         imageDenoisedNpArray = denoise(imageNpArray, denoiser)
     else:
-        imageDenoisedNpArray = means[color]
+        imageDenoisedNpArray = colorMeans[color]
     imageNoiseNpArray = imageNpArray - imageDenoisedNpArray
     estimatedPrnuIterativeMean.add(imageNoiseNpArray)
 
@@ -91,14 +91,14 @@ if (minColor is None or maxColor is None) and denoiser != 'mean':
     print(f'{maxColor=}')
 
 if denoiser == 'mean':
-    means = {}
+    colorMeans = {}
     for color in colors:
         colorIterativeMean = iterativeMean()
         for imageFileName in tqdm(imagesFileNames, f'Computing mean of {color} colored images'):
             imageNpArray = getImageNpArray(imageFileName, False, color)
             imageNpArray = gaussian_filter(imageNpArray, sigma = 5)
             colorIterativeMean.add(imageNpArray)
-        means[color] = colorIterativeMean.mean
+        colorMeans[color] = colorIterativeMean.mean
         fileName = f'mean_{imagesFolderPathFileName}_{color}'
         # Then use `merge_single_color_channel_images_according_to_bayer_filter.py` to consider all color channels, instead of saving this single color channel as an image.
         saveNpArray(fileName, colorIterativeMean.mean)