Generalization of Otsu's binarization into recursive colour image segmentation

In this paper we study ways to generalise Otsu's binarization method towards reduction of colour levels in colour images. Colour defines a multi-dimensional property vector at each pixel location, and this can be further generalised towards considering arbitrarily finite-dimensional property vectors at pixel locations. Otsu's binarization method, originally already briefly discussed by Otsu for multi-thresholding, was efficiently mapped earlier into a segmentation method for grey-level images by recursively applying the original binarization method. We generalise further by proposing a recursive algorithm for finite-dimensional property vectors at pixel locations. Experimental results demonstrate colour-level reduction by our method.