Efficient Removal of Real Time Rain Streaks from A Image using Novel Naive Bayes (NB) Compare over Linear Regression (LR) with Improved Accuracy

Abstract

Proposed study will examine the efficacy of removing real-time rain streaks from an image using novel NB and LR with the support of ML. Materials and Methods: A Realistic Single Image Dehazing (RESIDE) dataset has been collected from kaggle.com, which is a repository for our study. For all groups, a total sample of 22 was used. The proposed Naive Bayes algorithm is compared to the existing linear regression algorithms. The sample size is 44. Our proposed method includes steps for removing noise from images. For simulation, a pre-test power of 80% is used. Results: The proposed NB achieved an accuracy and sensitivity of 88.5% and 95.2%, whereas LR achieved an accuracy and sensitivity of 86.3% and 93%. The samples which are required for this investigation are calculated with the G power tool by fixing the minutest power to 0.8. In descriptive statistics, the observed effect size (p<0.05) in reference to the Naive Bayes and linear regression methods appeared significant. Conclusion: According to the experimental results, the novel NB algorithm performs significantly better than the existing LR.