Summary: This paper presents an algorithm for automatic neural image analysis in immunostained vertebrate retinas. We present a useful tool for cell quantification avoiding the losst of information of traditional binary techniques in automatic recognition of images. The application is based on the extension of the mathematical morphology to colour images. In the paper, we define the basics and more complex morphological operations to vectorial image processing. We propose and demonstrate a colour image reconstruction by geodesic transformations. In addition, we adapt the morphological segmentation of greyscale image to the segmentation of multispectral images of retinas of monkeys.