Structural Study of Heterogeneous Biological Samples by Cryoelectron Microscopy and Image Processing

Figure 8

K-Means Clustering. (a) Two initial seeds are randomly placed within the data. (b) Step  2 indicates positions of the averages of images that are nearest to the seeds. (c) The averages are then recalculated based on the assignments in step  2. Steps  2 and 3 are reiterated; (d) shows the final classes.

(a)

(b)

(c)

(d)