take_snapshot_next.py

        # Let's fetch the video frame we just captured
        imagePath = os.getcwd() + "/img_"+str(framesTaken)+".png"
        # Transform the image to an OpenCV readable image
        image = cv2.imread(imagePath)

        # Let's make a copy of this image
        # to use for the color palette generation
        image_copy = image_resize(cv2.cvtColor(
            image, cv2.COLOR_BGR2RGB), width=100)

        # Since the K-means algorithm we're about to do,
        # is very labour intensive, we will do it on a smaller image copy
        # This will not affect the quality of the algorithm
        pixelImage = image_copy.reshape(
            (image_copy.shape[0] * image_copy.shape[1], 3))

        # We use the sklearn K-Means algorithm to find the color histogram
        # from our small size image copy
        clt = KMeans(n_clusters=clusters+offset)
        clt.fit(pixelImage)

        # build a histogram of clusters and then create a figure
        # representing the number of pixels labeled to each color
        hist = centroid_histogram(clt)

        # Let's plot the retrieved colors. See the plot_colors function
        # for more details
        bar = plot_colors(hist, clt.cluster_centers_)

        # Resize the color bar to be even width with the video frame
        barImage = image_resize(
            cv2.cvtColor(bar, cv2.COLOR_RGB2BGR),
            width=int(videoSize[0]))

        # This is just a whitespace to put between the image and the color bar
        im = np.zeros((borderSize/2, int(videoSize[0]), 3), np.uint8)
        cv2.rectangle(im, (0, 0), (int(videoSize[0]), borderSize/2),
                      (255, 255, 255), -1)

        # Now we combine the video frame and the color bar into one image
        newImg = np.concatenate([image, im, barImage], axis=0)
        cv2.imwrite(imagePath, newImg)