International Academic Journal of Science and Engineering

  • ISSN 2454-3896

Modified Histogram Based Contrast Enhancement using Homomorphic Filtering for Medical Images

Farzad yaghoubi dizaji

Abstract: In medical image processing, low contrast image analysis is a challenging problem. In digital image processing contrast enhancement techniques are an important techniques for both human and computer vision. Low contrast digital images reduce the ability of observer in analyzing the image. Histogram based techniques are used to enhance contrast of all type of medical images. Histogram Equalization (HE) is one of the simplest and effective technique to perform contrast enhancement. In histogram equalization we reduce the number of gray levels by combining two or more less frequent neighboring gray levels in one gray level; also we stretch high frequent intensities over high range of gray levels to achieve comparatively more flat histogram. This flattering causes the overall enhancement of contrast of the input image. In histogram equalization we do not have any mechanism to control the enhancement level, due to this sometime output image have over enhanced regions. we propose a new method named “Modified Histogram Based Contrast Enhancement using Homomorphic Filtering" (MH-FIL) for medical images. This method uses two step processing, in first step global contrast of image is enhanced using histogram modification followed by histogram equalization and then in second step homomorphic filtering is used for image sharpening, this filtering if followed by image normalization. To evaluate the effectiveness of our method we choose two widely used metrics Absolute Mean Brightness Error (AMBE) and Entropy. Based on results of these two metrics this algorithm is proved as a flexible and effective way for medical image enhancement and can be used as a pre-processing step for medical image understanding and analysis

Keywords: Histogram Equalization, Contrast Enhancement, Homomorphic Filtering, Medical Image processing

Page: 265-273

Volume 2, Issue 2, 2015