No abstract

No abstract

The goal of any de-noising technique is to remove noise from an image which is the first step in any image processing. The noise removal method should be applied watchful manner otherwise artefacts can be introduced which may blur the image. In this work, three levels of Gaussian noise are used for adding noise on the original image (σ=10, σ=50, σ=100) and also (σ=15, σ=20, σ=25) to compare with Ramadhan et al.[1] and analysis with it to test embedded system with median filter. Performance evaluation of the median filter, wavelet threshold de-noising techniques is provided. The techniques used are namely the median filter and wavelet threshold is used to remove noise based on raspberry pi with Python. Four methods to remove noise image are used. MF, WT, MF before and after WT. The results showed the image of camera was better than other after tested all the methods with Gaussian noise σ=10. On other hand the other images were better than image of camera for the Gaussian level 50 and 100. The results were good in median filter in wavelet threshold based on Raspberry Pi, which is compared with overall result most of images butter in median filter. KEYWORDSImage Denoising Median Filter Wavelet Threshold Gaussian Noise This is an open-access article under the CC-BY-SA license This research devided in severap part. Section II explain the m methodology includes Literature Review, addition noise model, spatial domain filtering, Wavelet transform, Wavelet threshold, and the parameters. The results willo be delivered in Section III, includes Image Denoising, comparison benchmark. The last section (IV) shows the conclusion.

No abstract

Image denoising is a critical task in computer vision aimed at removing unwanted noise from images, which can degrade image quality and affect visual details. This study proposes a novel approach that combines deep hybrid learning with the Self-Improved Orca Predation Algorithm (SI-OPA) for image denoising. Leveraging Bidirectional Long Short-Term Memory (Bi-LSTM) and optimized Convolutional Neural Networks (CNN), the hybrid model aims to enhance denoising performance. The CNN’s weights are optimized using SI-OPA, resulting in improved denoising accuracy. Extensive comparisons against state-of-the-art denoising methods, including traditional algorithms and deep learning-based techniques, are conducted, focusing on denoising effectiveness, computational efficiency, and preservation of image details. The proposed approach demonstrates superior performance in all aspects, highlighting its potential as a promising solution for image-denoising tasks. Implemented in Python, the hybrid model showcases the benefits of combining Bi-LSTM, optimized CNN, and SI-OPA for advanced image-denoising applications.