Convert RGB image to index image

Question

I want to convert a 3 channel RGB image to a index image with Python. It\'s used for handling the labels of training a deep net for semantic segmentation. By index image I m

Answer 1

Here's a small utility function to convert images (np.array) to per-pixel labels (indices), which can also be a one-hot encoding:

def rgb2label(img, color_codes = None, one_hot_encode=False):
    if color_codes is None:
        color_codes = {val:i for i,val in enumerate(set( tuple(v) for m2d in img for v in m2d ))}
    n_labels = len(color_codes)
    result = np.ndarray(shape=img.shape[:2], dtype=int)
    result[:,:] = -1
    for rgb, idx in color_codes.items():
        result[(img==rgb).all(2)] = idx

    if one_hot_encode:
        one_hot_labels = np.zeros((img.shape[0],img.shape[1],n_labels))
        # one-hot encoding
        for c in range(n_labels):
            one_hot_labels[: , : , c ] = (result == c ).astype(int)
        result = one_hot_labels

    return result, color_codes


img = cv2.imread("input_rgb_for_labels.png")
img_labels, color_codes = rgb2label(img)
print(color_codes) # e.g. to see what the codebook is

img1 = cv2.imread("another_rgb_for_labels.png")
img1_labels, _ = rgb2label(img1, color_codes) # use the same codebook

It calculates (and returns) the color codebook if None is supplied.