Subject of study: We focused on images of transverse sections of the mammalian spinal cord belonging to its various segments. Aim of study: We selected optimal methods for assessing the similarity of images of transverse sections of the spinal cord obtained earlier in different histological studies. Method: We assessed the similarity of images of transverse sections of the spinal cord with the help of (a) Jaccard index (the size of the contour's intersection divided by the size of the contour's union), (b) metrics of distance between gray matter contours, (c) correlations between gray matter contours, and (d) the difference between gray matter contours based on Hu moments (a set of seven numbers calculated using central moments that are invariant to image transformations). Main results: Jaccard index and metrics of distances between contours allowed us to successfully determine the degree of similarity of sections obtained from the same animal. Hu invariant moments are suitable for the successful recognition of images of spinal cord segments obtained from various sources. Practical significance: The results suggest that the automated identification of spinal cord segments can be based on a comparison of histological or tomographic images of transverse sections of the spinal cord with some databases containing a set of reference images of particular segments. Such comparisons may be performed with the help of the contour similarity methods based on the Hu invariant moments. This work was supported by the Russian Science Foundation, project №21-15-00235.