Hybrid Discrete Wavelet Transform and Gabor Filter Banks Processing for Features Extraction from Biomedical Images.

Salim Lahmiri,Mounir Boukadoum

doi:10.1155/2013/104684

Salim Lahmiri, Mounir Boukadoum

Open Access

https://doi.org/10.1155/2013/104684

Copy DOI

Abstract

A new methodology for automatic feature extraction from biomedical images and subsequent classification is presented. The approach exploits the spatial orientation of high-frequency textural features of the processed image as determined by a two-step process. First, the two-dimensional discrete wavelet transform (DWT) is applied to obtain the HH high-frequency subband image. Then, a Gabor filter bank is applied to the latter at different frequencies and spatial orientations to obtain new Gabor-filtered image whose entropy and uniformity are computed. Finally, the obtained statistics are fed to a support vector machine (SVM) binary classifier. The approach was validated on mammograms, retina, and brain magnetic resonance (MR) images. The obtained classification accuracies show better performance in comparison to common approaches that use only the DWT or Gabor filter banks for feature extraction.

Highlights

Computer-aided diagnosis (CAD) has been the subject of a lot of research as a tool to help health professionals in medical decision making
We describe a hybrid biomedical image processing and classification system that uses both the discrete wavelet transform (DWT) and Gabor filter as directional transforms and statistical features derived from them for the classification task which is accomplished by support vector machines (SVMs) [36]
Mammograms and retina and brain magnetic resonance (MR) images corresponding to given pathologies are considered in this work, and the aim is to classify normal versus abnormal images for each image category

Summary

Introduction

Computer-aided diagnosis (CAD) has been the subject of a lot of research as a tool to help health professionals in medical decision making. Many CAD systems integrate image processing, computer vision, and intelligent and statistical machine learning methods to aid radiologists in the interpretation of medical images and help improve diagnostic accuracy. Because the segmentation step requires prior knowledge of discriminant image features and its implementation typically calls for numerous parameter settings, recent works have attempted to eliminate it These approaches realize feature space reduction by applying one or more transforms to the whole image and extracting the feature vector to classify from one or more of the obtained components [3, 5, 7,8,9,10,11,12,13,14]

Methods

Results

Conclusion