Evaluation of Correntropy Features for Normal/Glaucoma Images Employing Ridgelet Empirical Wavelet Transform

The adaptive representation of the signal is exceptionally vital in signal processing. Some current techniques, like the Empirical Mode Decomposition (EMD), decompose the signal suitable that comprises information but this approach has lacked theory. This paper addresses another procedure to foster versatile wavelets. The idea of this process is to extricate the various methods of a signal by planning a wavelet channel bank prompting the Empirical Wavelet Transform (EWT). Glaucoma is a major eye disease that causes the weakening of optic nerve fibers due to augmented fluid pressure. Previous methods of glaucoma diagnosis are costly, time taking, and required experienced clinicians to understand the eye problems. Consequently, in this paper, accurate and fast detection for glaucoma was presented. This paper gives an innovative idea for the diagnosis of glaucoma using Ridgelet EWT. Ridgelet Components and Frequency components were plotted. Correntropy features were evaluated for normal and glaucoma images and it's a significant change was observed.