multi class support vector machine

[jithin12]

Is it possible to implement multiclass support vector machine and probabilistic neural network using labview?

[Klemen]

Hello,

regarding the multiple classes SVM:

NI Vision Concepts Manual:

"SVM classification typically involves two classes. For applications that involve more than two classes, the SVM algorithm uses a one-versus-one approach. In a one-versus-one approach, the algorithm creates a binary classification model for every possible combination of classes, so that n number of classes produces n × (n – 1)/2 classification models. During classification, the algorithm uses a voting mechanism to identify the best class. If the voting mechanism identifies multiple classes, the algorithm selects the class that is closest to the sample."

Best regards,

K

[jithin12]

i am new to work with labview and neural network.. Can you share that VI.. my work requires classification of hand gestures like up , down, left , right etc using features like mean , energy , fft etc..

[Klemen]

Hello,

for starters, I suggest checking the NI Vison Concepts Manual to get a bit familiar with the libraries:

http://digital.ni.com/manuals.nsf/websearch/80C4CF7AFB49D89586257B98006D138A

Vision has libraries for fft, energy, mass, etc... calculations as well as two classification methods (SVM and nearest neighbour).

A SVM example for texture classification:

http://forums.ni.com/t5/Machine-Vision/I-use-a-classifier-file-generated-by-NI-Texture-Training/m-p/...

Best regards,

K