Effect of pure white on a color histogram

I am trying to use the KNN method to classify people in races based on their facial photos. I have a dataset on a pure white background [255, 255, 255].

I use the color bar chart values ​​as the feed input. I was told that I should remove the background color from the histogram to improve KNN performance.

Problem: When I create a mask from my photo that ignores the background, the histogram doesn't change one tiny bit.

Question: I'm not so into color theory that pure white affects the shape of the color histogram in general? When I use a regular mask that only centers (like in the image below), the histogram changes.

This is the mask I built on the picture, ignoring the background

Simple mask to check the correct application of the mask

Source image for histogram calculation

This is the histogram I get from the unmasked image and from my constructed mask, ignoring the white.

This is the histogram I get from cropping using my simple mask. histograms, so I believe my method of calculating the histogram is correct.

Code for calculating the histogram:

# loop over the image channels
for (chan, color) in zip(channels, colors):
    # create a histogram for the current channel and
    # concatenate the resulting histograms for each channel
    hist_full = opencv.calcHist([chan], [0], mask, [bin_amount], [0, bin_amount])

    # plot the histogram
    plt.plot(hist_full, color=color)
    plt.xlim([0, bin_amount])

plt.show()

      

        
        
        
      

    

The code to create the mask:

    mask = np.zeros(image.shape[:2], np.uint8)
    # simple mask option
    # mask[75:175, 75:175] = 255


    # create a mask to ignore white background in the histogram
    for row in range(0, len(image)):

        for col in range(0, len(image[0])):

            if (image[row][col] != np.asarray(prop.background)).all():
                try:
                    mask[row][col] = 255
                except IndexError:
                    print(col)