Workflows


Spine classification based on kernel density estimation

devrim's picture
Workflow Author: 

M U Ghani

Workflow Language: 
Dimension: 
2D
Input data type: 
image
Output data type: 
class labels
Comment / Instructions: 

We propose to use a kernel density estimation (KDE) based approach for classification. This non-parametric approach intrinsically provides the likelihood of membership for each class in a principled manner.
The implementation was used in [1].
Any papers using this code should cite [1] accordingly.

The software has been tested under Matlab R2013b.

References

  1. [Ghani2016] Ghani MUsman, Mesadi F, Kanık SDemir, Argunşah AÖzgür, Hobbiss AFelicity, Israely I, Ünay D, Taşdizen T, Çetin M
    2016.  Dendritic Spine Classification using Shape and Appearance Features based on Two-Photon Microscopy. Journal of Neuroscience Methods. :-.
Rating: 
0
No votes yet