Image mining using wavelet transform

  • Authors:

  • Sanjay T. Gandhe;K. T. Talele;Avinash G. Keskar

  • Affiliations:

  • Visvesvaraya National Institute of Technology, Nagpur, India;S.P. College of Engineering, Andheri (W), Mumbai, India;Visvesvaraya National Institute of Technology, Nagpur, India

  • Venue:
  • KES'07/WIRN'07 Proceedings of the 11th international conference, KES 2007 and XVII Italian workshop on neural networks conference on Knowledge-based intelligent information and engineering systems: Part I
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we propose an image mining using wavelet transform. It uses general pattern matching, pattern recognition and data mining concepts so that a real life scene/ image can be related to a particular category, helping in different prediction and forecasting mechanisms. It is a three-step process i.e. image gathering, learning and classification. As wavelet transform uses time frequency relation, it can be used for image mining instead of Fourier transform. Wavelet transform is used to decompose an image into different frequency sub bands and a low frequency sub band is used for Principal Component Analysis. Classification relates to identifying the category to which an image belongs. We have developed prototype system for recognition using DWT + PCA system. The concept of image mining thus can be efficiently used for weather forecasting so that we can know the natural disasters that may occur in advance.