New Frontiers in Communication and Intelligent Systems
Comparative Analysis and Implementation of CLAHE with Proposed Technique in Retinal Images
Authors: Rajwinder Kaur, Richa Brar and Gagandeep Jagdev
Publishing Date: 12-11-2021
ISBN: 978-81-95502-00-4
Abstract
The human eye is the most critical part that can be adversely affected by diabetes in the near or long run. The detection of DR (Diabetic Retinopathy) in the early stages is not that easily possible. The detection of DR primarily depends on the quality of the retinal images of the diseased person. The higher is the quality of the retinal image, the more are the chances of detection of abnormalities. The research paper elaborates on the popular CLAHE (Contrast Limited Adaptive Histogram Equalization) technique been used for enhancing the contrast of the retinal images. The research paper also anticipates a technique intended for enhancing the quality of the retinal images. The retinal images are obtained from the DRIVE (Digital Retinal Images for Vessel Extraction) dataset. The quality of enhancement achieved by using both techniques is compared and measured using three performance metrics of MSE (Mean Square Error), PSNR (Peak Signal Noise Ratio), and RMSE (Root Mean Square Error). PSNR is considered as the prominent performance metric to decide the degree of enhancement achieved. Greater is the value of the PSNR, higher is the degree of enhancement. The comparative analyses between the PSNR values obtained from both the techniques have been conducted and it has been found that the proposed technique outperforms CLAHE in enhancing the retinal images.
Keywords
Blood vessels, CLAHE, DRIVE, Enhancement, PSNR.
Cite as
Rajwinder Kaur, Richa Brar and Gagandeep Jagdev, "Comparative Analysis and Implementation of CLAHE with Proposed Technique in Retinal Images", In: Rahul Srivastava and Aditya Kr. Singh Pundir (eds), New Frontiers in Communication and Intelligent Systems, SCRS, India, 2021, pp. 69-76. https://doi.org/10.52458/978-81-95502-00-4-9