CODEWITHSUNDEEP
neural-networkcharacterimage-recognitionsvmlibsvm
user659976
user659976

Reputation: 1

How to train SVM for Tamil Character Recognition using MATLAB?

Hi I am doing my Final Year M.E Project in Tamil Character Recognition. I have completed till Feature Extraction step. Now I got Features for Each image in the Dataset(HP Labs). How to Feed these features to train SVM and How to Perform Class Labeling. I am new to this Neural Network area. So please Help me....

Upvotes: 0

Views: 1646

Answers (2)

raj
raj

Reputation: 21

In Training

In Matlab neural Network has two inputs:

  1. Input vector
  2. Target Vector

Example:

net = newFF(input,target);
net = train(net,input,target);

You give feature is input vector. Target is corresponding feature id(char ID).

In Testing

Extract feature from image, then test the feature in Neural Network using sim function. sim(net,features).. It returns corresponding char-ID.

open Matlab then type nftool and study that tool box.

same thing in SVM

Training

svmtrain(input,label). input as feature. label as ID of particular feature.

Testing

using svmclassify() method . It returns output of charID.

Upvotes: 2

Krishnamurthy
Krishnamurthy

Reputation: 715

you may want to look at the svmclassify and svmtrain methods in the bioinformatics toolbox in matlab.

by the way, do you really want support vector machines or neural networks? they are very different from each other. please be clear which classifier you want to use for your problem before deciding to use a particular implementation.

if you are new to the field of machine learning and want to try out a couple of algorithms, I would suggest you try Weka first.

Upvotes: 0

Related Questions