Image Denoising Using Hybrid Deep Learning Approach and Self-Improved Orca Predation Algorithm

• Published in: Technologies (Basel) Vol. 11; no. 4; p. 111
• Main Authors: Jebur, Rusul Sabah, Zabil, Mohd Hazli Bin Mohamed, Hammood, Dalal Abdulmohsin, Cheng, Lim Kok, Al-Naji, Ali
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-08-2023
• Subjects: Algorithms; Artificial intelligence; Artificial neural networks; Bi-LSTM; CNN; Comparative analysis; Computer vision; Datasets; Deep learning; Image degradation; image denoising; Image processing; Image quality; Literature reviews; Machine learning; Methods; Neural networks; Noise reduction; Optimization algorithms; Performance evaluation; Regularization methods; SI-OPA; Tomography; Wavelet transforms; Malaysia
• ISSN: 2227-7080; 2227-7080
• DOI: 10.3390/technologies11040111

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.