Back
Automatic particle picking using diffusion filtering and random forest classification
An automatic particle picking algorithm for processing electron micrographs of a large molecular complex, the 26S proteasome, is described. The algorithm makes use of a coherence enhancing diffusion filter to denoise the data, and a random forest classifier for removing false positives. It does not make use of a 3D reference model, but uses a training set of manually picked particles instead. False positive and false negative rates of around 25% to 30% are achieved on a testing set. The algorithm was developed for a specific particle, but contains steps that should be useful for developing automatic picking algorithms for other particles.
@inproceedings{JoubertNBHHS2011, title = {Automatic particle picking using diffusion filtering and random forest classification}, abstract = {An automatic particle picking algorithm for processing electron micrographs of a large molecular complex, the 26S proteasome, is described. The algorithm makes use of a coherence enhancing diffusion filter to denoise the data, and a random forest classifier for removing false positives. It does not make use of a 3D reference model, but uses a training set of manually picked particles instead. False positive and false negative rates of around 25% to 30% are achieved on a testing set. The algorithm was developed for a specific particle, but contains steps that should be useful for developing automatic picking algorithms for other particles.}, pages = {6}, month = sep, year = {2011}, slug = {joubertnbhhs2011}, author = {Joubert, P. and Nickell, S. and Beck, F. and Habeck, M. and Hirsch, M. and Sch{\"o}lkopf, B.}, month_numeric = {9} }