View Feed
group-icon
Coffee Room
Discuss anything here - everything that you wish to discuss with fellow engineers.
12916 Members
Join this group to post and comment.
sherly
sherly • Feb 13, 2009

k nn classifier

hi
i am working in classification of texture images.
can anyone help me with a code for k nearest neighbour classifier and also help me to create a training dataset with labelled categories.
deepmali
deepmali • Feb 16, 2009
hi
I am also doing something similar..I am using SVD based approach...If you have any info pls post it here.
sherly
sherly • Feb 23, 2009
classification rate

hi,
I am working on image classification.
I am using minimum distance classifier.
Can anyone help me with the formula for correct classification rate.
Thank you.
Predictor
Predictor • Mar 14, 2009
Re: classification rate

sherly
hi,
I am working on image classification.
I am using minimum distance classifier.
Can anyone help me with the formula for correct classification rate.
I think that what you are referring to is simply the accuracy of the classifier, which is defined as: the number of correct classifications divided by the total number of classifications.


-Will Dwinnell
Data Mining in MATLAB
Predictor
Predictor • Mar 14, 2009
sherly
hi
i am working in classification of texture images.
can anyone help me with a code for k nearest neighbour classifier and also help me to create a training dataset with labelled categories.
k-nearest neighbors is very simple:

1. Calculate the distance from the current case to all historical cases.
2. Select the k historical cases with the least distance from the current case.
3. Merge those k cases, typically by averaging for numeric estimation problems or by voting for classification problems.


-Will Dwinnell
Data Mining in MATLAB

Share this content on your social channels -