I am working in Iris recognition and I want to extract features from a normalised iris pattern using Haar transform. I am trying to follow the method given in 'Shinyoung Lim et al. Efficient Iris Recognition Through Improvement of Feature Vector and Classifier, ETRI Journal, Volume 23, 2001'.
The basic idea is applying Haar transform on an image of size 450*60 and obtain the last HH pattern (which will be of 28*3 size), But I couldn't implement/use any Haar transform working for images which is not of square (n*n) dimension.
Any suggestion is appreciated.