MATLAB Central Newsreader - Neural Network Training for Image Classification

Re: Neural Network Training for Image Classification

Tak — Thu, 12 Feb 2009 21:21:01 -0500

Hi, would you mind take a look and answer this stupid question in http://www.mathworks.com/matlabcentral/newsreader/view_thread/243425#624974 ? Thanks

Neural Network Training for Image Classification

Jeevashini — Tue, 27 Jan 2009 14:14:01 -0500

Hi,

I am working on image classification based on colour histograms. I have 4 classes of images. Each class of images have a different colour dominant in them. For each image I have HSV histogram. The HSV histogram is made from 8 bins for Hue, 2 bins each for Saturation and Value. Therefore each image has a vector of 32 data.

I have 65 training images in each of the 4 classes: total of 260 images.
I need to feed the 32x260 matrix to train the neural network.

My objective is to compare two methods in classification. One is classifying the image as a whole. Other is dividing an image into blocks and classifying them individually, then finally based on some voting method or some other method classify the image as a whole.

I have basically two questions in carrying out this process.

1. Does having 8x2x2=32 HSV histograms suffice for the training process?
2. For the second method of classification, do I have to perform training separately on the individual blocks? Or can I use the trained network in the first method(whole image classification) for classifying the blocks?

Some advice would be helpful, please.

Thanks,
Vashini

Re: Neural Network Training for Image Classification

Tak — Sat, 31 Jan 2009 10:12:02 -0500

what is the meaning of 8x2x2=32 HSV histograms ?

I am doing in the similar thing. I use wavelet transform to decompose the image into 16 features for each images. I want to know more alternative method too :)

Re: Neural Network Training for Image Classification

Jeevashini — Wed, 04 Feb 2009 20:22:01 -0500

"Tak " <lauhotak@hotmail.com> wrote in message <gm185i$klu$1@fred.mathworks.com>...
> what is the meaning of 8x2x2=32 HSV histograms ?
>
It means Hue has 8 bins, Saturation and Value has 2 bins each. Therefore, as a combination of each of the 8 Hue bins to each of the 2 Saturation bins and 2 Value bins, we get 32 HSV bins. That will be used as the input vector.

Re: Neural Network Training for Image Classification

Jeevashini — Wed, 04 Feb 2009 20:24:02 -0500

Please, it would be helpful if someone could give me some advice on this.

Thanks,
Vashini