ML2DClassification

ML2D Classification and Alignment

• Perform a maximum-likelihood multi-reference refinement.
• Visualize the classes and class averages of the multi-reference refinement. (For the most challenging cases, one may further subdivide each of the classes obtained using self-organizing maps, as explained in the next protocol)

Example Data

• Input
  • Gallery of images.

File ml2d_classification.tar.gz contains the images and the xmipp_protocol_ml2d.py script necessary to run theml2d_classification protocol. In this example theml2d_classification script is used for aligning the two classes (simC6.sel and simC3.sel) identified by therotational_spectra_classification script in theRotationalSpectraClassification.

• Output, for each iteration
  • Average image per class
  • Docfile with the optimal alignment parameters is saved (the optimal alignment parameters are NOT stored in the image headers!).
  • Log files, with log-likelihood target function value, class sizes etc.

File output_ml2d_classification.tar.gz contains the results of executing the[[ML2D]] script.

Pressanalyze results button for visualizing the classification.

/output_ml2d_classification.jpg

average image for the different iterations and plots of several magnitudes used to monitor the algorithm convergence

## USER's COMMENTS