Ask Your Question
1

how to recognize different postures of hand

asked 2013-08-14 01:49:09 -0500

VoidMee gravatar image

updated 2013-08-14 04:17:29 -0500

Hello, I want to train and recogninze three postures of hand using neural network in Opencv. So, I have many question regarding it:

  1. (High Priority) Is it better to use Neural Network Machine Learning Library or create Haar Classifier for this kind of problem?
  2. What does the feature vector mean in ANN_MLP::train function and how to calculate these features?
  3. How to put features from multiple images in this ANN_MLP?

Thank you very much, a lot!

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted
2

answered 2013-08-14 04:23:35 -0500

Q1: it all depends on your application and the amount of training data you have. The advantage of a haar wavelet classifier is that you can easily manipulate parameters throughout the complete process, whereas neural networks are trained and noone has a real idea of how the internal structure looks like. This is one of the main reason why the interest in neural networks has been less in the last couple of years.

Q2: the feature vector is basically the properties from the image you want to use for classification by the neural network. These can be calculated using different techniques which are focussed in the machine learning and the features2D module of the openCV library. You should have a look at the tutorials to see how they actually work.

Q3: this is basically providing a matrix of data to the multiple layer perceptron by using the rows as data vectors and the columns as elements of different images.

However, looking at your questions, I suggest you first go find yourself some documentation on the basic concepts of multilayer perceptrons and how they work, because the questions just illustrate that you have no idea on how it actually works.

edit flag offensive delete link more

Comments

Thank you very much for your such an illustrated answer.

Regarding feature vector, is the descriptor or keypoints that we take as training data.

And, for each image the extractor extracts multidimensional data. so how to feed this multidimensional data each row of 128 long vector with 128 input nodes in input layer.

VoidMee gravatar imageVoidMee ( 2013-08-16 10:04:08 -0500 )edit
Login/Signup to Answer

Question Tools

Stats

Asked: 2013-08-14 01:49:09 -0500

Seen: 188 times

Last updated: Aug 14 '13