reads a image file and returns a list of tuples with the rgb values and the number of pixels with that color, sorted by the number of pixels

count_distinct_color_values.py

#v reads a image file and returns a list of tuples with the rgb values and the number of pixels with that color, sorted by the number of pixels
import sys
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import pprint

def quantize(val):
    return val
def count_distinct_color_values(filepath):
    img = mpimg.imread(filepath)
    colors = {}
    totalPixels = len(img) * len(img[0])
    n = 0
    for row in img:
        for pixel in row:
            pixel_I32 = quantize(pixel[0]) << 16 | quantize(pixel[1]) << 8 | quantize(pixel[2])
            if pixel_I32 in colors:
                colors[pixel_I32] += 1
            else:
                colors[pixel_I32] = 1
            # report progress every 100000 pixels
            if n % 100000 == 0:
                print('processed %d of %d pixels' % (n, totalPixels))
            n += 1

    return sorted(colors.items(), key=lambda x: x[1], reverse=True)

if __name__ == '__main__':
    colorCounts = count_distinct_color_values(sys.argv[1] if len(sys.argv) > 1 else 'test.jpg')
    # pprint.pprint(colorCounts)
    # only print the top 10 colors
    pprint.pprint(colorCounts[:10])
    # print the top 10 colors as hex values
    pprint.pprint([(hex(color[0]), color[1]) for color in colorCounts[:10]])