Analysis of Combination Algorithms for Denoising and Contrast Enhancement Images
DOI:
https://doi.org/10.26555/jiteki.v8i2.22216Abstract
Reducing noise and increasing image contrast is part of the purpose of enhancing image quality; instead, it will impact change the diversity of information in the image based on the Shannon entropy value. Decrease quality caused by noise salt and pepper in this research or abnormal contrast in the image causes objects in the image to become unclear. Low contrast has a major impact on image quality, including noise reduction processes affecting image information so that the quality of the reduced image becomes something to consider for large noise. Iterative Denoising and Backward Projections with CNN (IDBP-CNN) and Different Applied Median Filter (DAMF) is a good solution for denoising a large percentage of noise with good quality results image. In other research for contrast enhancement, Triangular Fuzzy Membership-Contrast Limited Adaptive Histogram Equalization (TFM-CLAHE) and Adaptive Fuzzy Contrast Enhancement Algorithm with Details Preserving (AFCEDP) is claimed to a good solution to solve low contrast of the image. Therefore, this study is to find the best combination of denoising and contrast enhancement to get good image results with step denoising followed by contrast enhancement. Based on the experimental testing is got the best combination is the DAMF + AFCEDP algorithm with an average of PSNR 35dB and an average difference Shannon entropy of 0.0130.Downloads
Published
2022-06-08
Issue
Section
Articles
License
Authors who publish with JITEKI agree to the following terms:
- Authors retain copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
This work is licensed under a Creative Commons Attribution 4.0 International License