After obtaining an image of a biological specimen, image analysis system 100 may pass the image to superpixel generator 110. Superpixel generator 110 may receive the image and divide it (i.e., group its pixels) into a plurality of superpixels. Each superpixel may include a perceptually meaningful atomic region comprising a plurality of pixels. Superpixels can capture local image redundancy and provide a convenient primitive from which the image features can be computed, as discussed below. Processing the image in units of superpixels is generally much more computationally efficient than pixel based processing, especially for very high resolution images such as images of biological specimens. Superpixel generator 110 can generate (i.e., group the pixels into) superpixels using any of the available techniques, such as the techniques described in R. Achanta, A. Shaji, K. Smith, A Lucchi, P. Fua and S. Susstrunk, “SLIC superpixels compared to state-of-art superpixel methods,” in Pattern Analysis and Machine Intelligence 2012; P. Felzenszwalb and D. Huttenlocher, “Efficient Graph-Based Image Segmentation,” in Intl J. Computer Vision, vol. 59, no. 2, pp. 167-181, September 2004; A. Levinshtein, A. Stere, K. Kutulakos, D. Fleet, S. Dickinson, and K. Siddiqi, “Turbopixels: Fast superpixels using geometric flows,” in IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2009; J. Shi and J. Malik, “Normalized cuts and image segmentation,” in IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 22(8):888-905, August 2000; and/or O. Veksler, Y. Boykov, and P. Mehrani, “Superpixels and supervoxels in an energy optimization framework,” in European Conference on Computer Vision (ECCV), 2010. It is appreciated that in some embodiments, the biological sample image obtained by system 100 may have already been divided into superpixels, i.e., superpixel boundaries have been already generated and provided to system 100, in which case superpixel generator 110 may be omitted from or disabled in system 100.