| Autor: |
Dinesh, K. Sai, Uganya, G. |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2023, Vol. 2587 Issue 1, p1-9, 9p |
| Abstrakt: |
Machine learning techniques are used in the area of digital image processing due to its impressive results in deconvolution of blurred images. The objective of this study is to evaluate the performance of the Novel ANN algorithm in deblurring of images by comparing it with the RLD algorithm. Novel Artificial Neural Network (ANN) and Richardson-Lucy Deconvolution (RLD) algorithms were implemented to deblur the input images upto 256 pixels range. These algorithms were implemented to enhance the accuracy rate of deblurred images using MATLAB Software. Sample size was calculated from clincalc.com with previous literature and it was analyzed by collecting the dataset of 20 samples with 80% of pretest power. From the MATLAB simulation result, Novel ANN achieves image deblurring rate with 93.08% accuracy and RLD method achieves image deblurring rate with 80.10% accuracy. The significance value obtained as 0.002 (P<0.05). Novel ANN classifier appears to have better accuracy compared to RLD Classifier. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
