0

I am posting 3 images of my dataset to show how my image visually looks:

http://s1306.photobucket.com/user/Bidisha_Chakraborty/library/?page=1

I am using VLFFeat DSIFT implementation. I am using per descriptor 4 orientations instead of 8. So in my case it is 64 dimensional vector instead of 128. I am using the original scale for the image, since my image data does is originally taken from fixed distance. I am computing descriptors densely at 4/8 pixels interval. I have conducted several experiments by varying the window size from 80*80 pixels to 20*20 pixels. I did a clustering approach with various number of cluster centers. And finally I used earth mover's Distance to compute the similarity metric. After various parameter tuning of window size, number of words, I see that even when I have nearly similar images like 1 and 3, the distance metric says image 1 is more similar to image 2 then image 1 to image 3.

I did Principal Component Analysis to see the variance of the data. I expected image 1 and image 2 to have separated clusters and image 1 and 3 to have overlapped clusters. Since I plotted first 3 dimensions and these 3 dimensions accounted for less than 30percentage of data, I am sure including all dimensions(which I of course could not visualize) will give worse results.

  1. Should I conclude that SIFT is not the best thing for my application or I am missing out something. I already used GLCM for these and did not get a good result. Any suggestion for any other feature space is most welcome. thanks for any kind of insight.
Bidisha Chakraborty
  • 1
  • Have you tried varying the amount of smoothing/blurring you do before feature extraction? –  Mar 23 '13 at 04:08
  • You may be correct that SIFT (and other local texture features) are not the best for this task, since your images are relatively textureless. –  Mar 23 '13 at 04:08
  • Yes. I tried smoothing the images. But since I am using equal smoothing on all images, it does not effect the results. – Bidisha Chakraborty Mar 23 '13 at 13:31

0 Answers0