Abstract
A novel Modified Histogram Equalization (MHE) technique for contrast enhancement is proposed in this paper. This technique modifies the probability density function of an image by introducing constraints prior to the process of histogram equalization (HE). These constraints are formulated using two parameters which are optimized using swarm intelligence. This technique of contrast enhancement takes control over the effect of HE so that it enhances the image without causing any loss to its details. A median adjustment factor is then added to the result to normalize the change in the luminance level after enhancement. This factor suppresses the effect of luminance change due to the presence of outlier pixels. The outlier pixels of highly deviated intensities have greater impact in changing the contrast of an image. This approach provides a convenient and effective way to control the enhancement process, while being adaptive to various types of images. Experimental results show that the proposed technique gives better results in terms of Discrete Entropy and SSIM values than the existing histogram-based equalization methods.
Highlights
Contrast enhancement plays a vital role in image processing for both human and computer vision
We propose a Modified Histogram Equalization (MHE) method by extending Weighted Thresholded HE (WTHE) [14]
The performance of the newly developed method, MHE is tested on various standard images such as Einstein, Village, Bottle, House, Peppers and Truck, out of which Einstein and Village are given in Fig. 2(a) and 4(a) respectively
Summary
Contrast enhancement plays a vital role in image processing for both human and computer vision. Global Histogram Equalization (GHE) uses the histogram information of the entire input image in its transformation function Though this global approach is suitable for overall enhancement, it fails to preserve the local brightness features of the input image. The high computational cost of LHE can be minimized using non-overlapping block based HE These methods produce an undesirable checkerboard effects on enhanced images. BBHE divides the input image histogram into two parts, based on the mean brightness of the image and each part is equalized independently This method tries to overcome the problem of brightness preservation. MMBEBHE is an extension of BBHE method that provides maximal brightness preservation Though these methods can perform good contrast enhancement, they cause annoying side effects depending on the variation of gray level distribution in the histogram.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
