Thread Subject: Neural Network Training for Image Classification

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

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 :)

"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.

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

Thanks,
Vashini

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