A Fast Classification Method for Single-Particle Projections with a Translation and Rotation Invariant

2013 ◽  
Vol 31 (2) ◽  
pp. 137-153
Author(s):  
Xia Wang and Guoliang Xu
2020 ◽  
Vol 57 (18) ◽  
pp. 182801
Author(s):  
李冶 Li Ye ◽  
张磊 Zhang Lei ◽  
何思远 He Siyuan ◽  
张云华 Zhang Yunhua ◽  
朱国强 Zhu Guoqiang

2013 ◽  
Vol 299 ◽  
pp. 168-171
Author(s):  
Qian Wang

A fast classification method of hyperspectral image is presented to resolve these problems caused by large processing data and noise influence. First, space information is used to extract Spatial Region Feature Spectral. Next, the non-linear method of feature extraction is used to extract the feature of SRFS. The simulation results show that the method can significantly improve the classification results of classifiers and reduce computing time.


2017 ◽  
Vol 24 (4) ◽  
pp. 701-720 ◽  
Author(s):  
Jiang Cui ◽  
Ge Shi ◽  
Chunying Gong

AbstractFault detection and location are important and front-end tasks in assuring the reliability of power electronic circuits. In essence, both tasks can be considered as the classification problem. This paper presents a fast fault classification method for power electronic circuits by using the support vector machine (SVM) as a classifier and the wavelet transform as a feature extraction technique. Using one-against-rest SVM and one-against-one SVM are two general approaches to fault classification in power electronic circuits. However, these methods have a high computational complexity, therefore in this design we employ a directed acyclic graph (DAG) SVM to implement the fault classification. The DAG SVM is close to the one-against-one SVM regarding its classification performance, but it is much faster. Moreover, in the presented approach, the DAG SVM is improved by introducing the method of Knearest neighbours to reduce some computations, so that the classification time can be further reduced. A rectifier and an inverter are demonstrated to prove effectiveness of the presented design.


Author(s):  
J. Frank ◽  
P.-Y. Sizaret ◽  
A. Verschoor ◽  
J. Lamy

The accuracy with which the attachment site of immunolabels bound to macromolecules may be localized in electron microscopic images can be considerably improved by using single particle averaging. The example studied in this work showed that the accuracy may be better than the resolution limit imposed by negative staining (∽2nm).The structure used for this demonstration was a halfmolecule of Limulus polyphemus (LP) hemocyanin, consisting of 24 subunits grouped into four hexamers. The top view of this structure was previously studied by image averaging and correspondence analysis. It was found to vary according to the flip or flop position of the molecule, and to the stain imbalance between diagonally opposed hexamers (“rocking effect”). These findings have recently been incorporated into a model of the full 8 × 6 molecule.LP hemocyanin contains eight different polypeptides, and antibodies specific for one, LP II, were used. Uranyl acetate was used as stain. A total of 58 molecule images (29 unlabelled, 29 labelled with antl-LPII Fab) showing the top view were digitized in the microdensitometer with a sampling distance of 50μ corresponding to 6.25nm.


Author(s):  
Adriana Verschoor ◽  
Ronald Milligan ◽  
Suman Srivastava ◽  
Joachim Frank

We have studied the eukaryotic ribosome from two vertebrate species (rabbit reticulocyte and chick embryo ribosomes) in several different electron microscopic preparations (Fig. 1a-d), and we have applied image processing methods to two of the types of images. Reticulocyte ribosomes were examined in both negative stain (0.5% uranyl acetate, in a double-carbon preparation) and frozen hydrated preparation as single-particle specimens. In addition, chick embryo ribosomes in tetrameric and crystalline assemblies in frozen hydrated preparation have been examined. 2D averaging, multivariate statistical analysis, and classification methods have been applied to the negatively stained single-particle micrographs and the frozen hydrated tetramer micrographs to obtain statistically well defined projection images of the ribosome (Fig. 2a,c). 3D reconstruction methods, the random conical reconstruction scheme and weighted back projection, were applied to the negative-stain data, and several closely related reconstructions were obtained. The principal 3D reconstruction (Fig. 2b), which has a resolution of 3.7 nm according to the differential phase residual criterion, can be compared to the images of individual ribosomes in a 2D tetramer average (Fig. 2c) at a similar resolution, and a good agreement of the general morphology and of many of the characteristic features is seen.Both data sets show the ribosome in roughly the same ’view’ or orientation, with respect to the adsorptive surface in the electron microscopic preparation, as judged by the agreement in both the projected form and the distribution of characteristic density features. The negative-stain reconstruction reveals details of the ribosome morphology; the 2D frozen-hydrated average provides projection information on the native mass-density distribution within the structure. The 40S subunit appears to have an elongate core of higher density, while the 60S subunit shows a more complex pattern of dense features, comprising a rather globular core, locally extending close to the particle surface.


Sign in / Sign up

Export Citation Format

Share Document