Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Last revision Both sides next revision | ||
|
eyes:logics:classification [2017/06/02 13:15] jschlie1 [Modes] |
eyes:logics:classification [2017/06/06 17:32] nfische [Concept] |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| ======Classification====== | ======Classification====== | ||
| - | **Classification** or **cluster analysis** groups similar objects in distinct clusters (in the EM Field usually called **classes**) while minimizing the variance (of a certain parameter) within one cluster/class. During image processing, classification is used to find similar 2D images within a dataset. | + | **Classification** or **cluster analysis** groups similar objects in distinct clusters (in the EM Field usually called **classes**) while minimizing the variance (of a certain parameter) within one cluster/class. During image processing, classification is used to find similar 2D images within a dataset, but also similar 3D structures within a set of structures. |
| =====Usage===== | =====Usage===== | ||
| - | A prerequisite for a feasible **classification** is a complexity reduction of the given input dataset. This can be achieved by performing a [[:eyes:logics:pca|principle component analysis (PCA)]]. The PCA can be carried out either internally by the classification-logic or beforehand by the respective PCA logic. Additionally, the user has to define the input set and the number of expected classes/clusters. Now, the logic will split the dataset according to the information provided by the PCA into as many classes/clusters as determined aiming for minimal variance within each class/cluster. | + | A prerequisite for a feasible **classification** is a complexity reduction of the given input dataset. This can be achieved by performing a [[:eyes:logics:pca]]. The PCA can be carried out either internally by the classification-logic or beforehand by the respective PCA logic. Additionally, the user has to define the input set and the number of expected classes/clusters. Now, the logic will split the dataset according to the information provided by the PCA into as many classes/clusters as determined aiming for an optimum of i) minimal variance within each class/cluster and ii) a maximized signal-to-noise ratio. |
| ===== Example ==== | ===== Example ==== | ||
| Line 14: | Line 14: | ||
| |< 100% 30% >| | |< 100% 30% >| | ||
| ^ Parameters ^ Description ^ | ^ Parameters ^ Description ^ | ||
| - | | Eigen images location | Define, whether the Eigen images used for complexity reduction are generated on-the-fly internally (intern) or provided by an input from en external source (extern) | + | | Eigen images location | Define, whether the Eigen images used for complexity reduction are generated on-the-fly internally (intern) or provided by an input from en external source (extern) | |
| - | | -> Number of eigen images | How many Eigen images (and therefore dimensions) should be used as components during linear combination | + | | -> Number of eigen images | How many Eigen images (and therefore dimensions) should be used as components during linear combination | |
| - | | Split up method | Determine, whether large classes should be slip up into smaller classes due to their number of containing objects (size) or due to their high internal variance of the cross-correlation-coefficients (cccVariance) | | + | | Split up method | Determine, whether large classes should be split into smaller classes i) to obtain classes containing a similar number of images/volumes (Cluster size) or ii) to minimize internal variance within each class, as measured by the cross-correlation-coefficients (cccVariance) | |
| | Number of classes | Number of resulting classes/clusters | | | Number of classes | Number of resulting classes/clusters | | ||
| - | | Remove duplicated images | FIXME ??? | | + | | Remove duplicated images | Duplicate images identified by the classification are removed | |
| |< 100% 30% >| | |< 100% 30% >| | ||
| ^ Input ^ Description ^ | ^ Input ^ Description ^ | ||
| | Input | Stack of input images | | | Input | Stack of input images | | ||
| - | | Pre. Eigen Images | (Only available, if //Eigen images location = extern//) Stack of Eigen images with the sum of all images and a mask as the last two images | | + | | //Pre Eigen Images// | (Only available, if //Eigen images location = extern; i.e. Eigen images precomputed with [[eyes:logics:PCA]] logic//) Stack of Eigen images with the sum of all images and a mask as the last two images | |
| |< 100% 30% >| | |< 100% 30% >| | ||
| Line 34: | Line 34: | ||
| | ClassID | ID of the class/cluster, the image belongs to | | | ClassID | ID of the class/cluster, the image belongs to | | ||
| - | =====Concept===== | + | ===== Concept ===== |
| - | Once clusters/classes of images are found, they can be averaged (see [[eyes:logics:sumbyclassnumber]]) to improve the signal-to-noise-ration dramatically.((van Heel, M. (1984). Multivariate statistical classification of noisy images (randomly oriented biological macromolecules). Ultramicroscopy, 13(1-2), 165–83. Retrieved from http://www.ncbi.nlm.nih.gov/pubmed/6382731)) | + | Once clusters/classes of images are found, they can be averaged (see [[eyes:logics:SumByClassNumber]]) to improve the signal-to-noise-ratio substantially.((van Heel, M. (1984). Multivariate statistical classification of noisy images (randomly oriented biological macromolecules). Ultramicroscopy, 13(1-2), 165–83. Retrieved from http://www.ncbi.nlm.nih.gov/pubmed/6382731)) |