Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Multiframe Image Restoration Using Generative Adversarial Networks


Affiliations
1 Department of Computer science and Technology, Karpagam College of Engineering, India
2 Department of Computer Science and Engineering, Manipur Institute of Technology, Manipur University Campus, India
3 Department of Computer Engineering, Dwarkadas Jivanlal Sanghvi College of Engineering, India
4 Department of Computer Science and Engineering, Indian Institute of Technology Jammu, India
     

   Subscribe/Renew Journal


This paper introduces a novel approach for multiframe image restoration using Generative Adversarial Networks (GANs). Traditional image restoration techniques often struggle with handling complex degradation patterns and noise in images. In contrast, GANs have demonstrated remarkable capability in generating realistic and high-quality images. The proposed method leverages the power of GANs to restore multiframe degraded images by training the generator to learn the underlying clean image from a set of degraded frames. The discriminator collaborates with the generator to ensure the fidelity of the restored output. Experimental results on various datasets show that the proposed multiframe image restoration approach achieves superior performance compared to state-of-the-art methods in terms of image quality and fidelity.

Keywords

Multiframe, Image Restoration, Generative Adversarial Networks (GANs), Degradation Patterns, Fidelity.
Subscription Login to verify subscription
User
Notifications
Font Size

  • M. Bhende and V. Saravanan, “Deep Learning-Based Real-Time Discriminate Correlation Analysis for Breast Cancer Detection”, BioMed Research International, Vol. 2022, pp. 1-11, 2022.
  • S. Gupta, M.R. Abonazel and K.S. Babu, “Supervised Computer-Aided Diagnosis (CAD) Methods for Classifying Alzheimer Disease-Based Neurodegenerative Disorders”, Computational and Mathematical Methods in Medicine, Vol. 2022, pp. 1-8, 2022.
  • C. Xu, P. Gao and J. Xu, “Image Enhancement Algorithm based on Generative Adversarial Network in Combination of Improved Game Adversarial Loss Mechanism”, Multimedia Tools and Applications, Vol. 79, pp. 9435-9450, 2020.
  • Z. Chen, P. Dai and P. Ouyang, “DN-GAN: Denoising Generative Adversarial Networks for Speckle Noise Reduction in Optical Coherence Tomography Images”, Biomedical Signal Processing and Control, Vol. 55, pp. 101632-101639, 2020.
  • H. Liu, T. Wang and S. Li, “Satellite Video Super-Resolution based on Adaptively Spatiotemporal Neighbors and Nonlocal Similarity Regularization”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 58, No. 12, pp. 8372-8383, 2020.
  • S. Gregory and Y. Gan, “HydraNet: A Multi-Branch Convolutional Neural Network Architecture for MRI Denoising”, Medical Imaging, Vol. 115, pp. 881-889, 2021.
  • B. Subramanian, T. Gunasekaran and S. Hariprasath, “Diabetic Retinopathy-Feature Extraction and Classification using Adaptive Super Pixel Algorithm”, International Journal on Engineering Advanced Technology, Vol. 9, pp. 618-627, 2019.
  • Y. Zhang, L. Zhao and L. Wang, “FRAGAN-VSR: Frame-Recurrent Attention Generative Adversarial Network for Video Super-Resolution”, Proceedings of IEEE International Conference on Tools with Artificial Intelligence, pp. 753-757, 2021.
  • D. Irfan, S. Srivastava and V. Saravanan, “Prediction of Quality Food Sale in Mart using the AI-Based TOR Method”, Journal of Food Quality, Vol. 2022, pp. 1-12, 2022.
  • B. Xu and H. Yin, “A Slimmer and Deeper Approach to Deep Network Structures for Low‐Level Vision Tasks”, Expert Systems, Vol. 78, pp. 13092-13098, 2022.
  • K.N.G. Veerappan, J. Perumal and S.J.N. Kumar, “Categorical Data Clustering using Meta Heuristic Link-Based Ensemble Method: Data Clustering using Soft Computing Techniques”, Proceedings of IEEE International Conference on Dynamics of Swarm Intelligence Health Analysis for the Next Generation, pp. 226-238, 2023.
  • G. Kiruthiga, “Improved Object Detection in Video Surveillance using Deep Convolutional Neural Network Learning”, International Journal for Modern Trends in Science and Technology, Vol. 7, No. 11, pp. 108-114, 2021

Abstract Views: 123

PDF Views: 1




  • Multiframe Image Restoration Using Generative Adversarial Networks

Abstract Views: 123  |  PDF Views: 1

Authors

M. Velammal
Department of Computer science and Technology, Karpagam College of Engineering, India
Thiyam Ibungomacha Singh
Department of Computer Science and Engineering, Manipur Institute of Technology, Manipur University Campus, India
Nilesh Madhukar Patil
Department of Computer Engineering, Dwarkadas Jivanlal Sanghvi College of Engineering, India
Subharun Pal
Department of Computer Science and Engineering, Indian Institute of Technology Jammu, India

Abstract


This paper introduces a novel approach for multiframe image restoration using Generative Adversarial Networks (GANs). Traditional image restoration techniques often struggle with handling complex degradation patterns and noise in images. In contrast, GANs have demonstrated remarkable capability in generating realistic and high-quality images. The proposed method leverages the power of GANs to restore multiframe degraded images by training the generator to learn the underlying clean image from a set of degraded frames. The discriminator collaborates with the generator to ensure the fidelity of the restored output. Experimental results on various datasets show that the proposed multiframe image restoration approach achieves superior performance compared to state-of-the-art methods in terms of image quality and fidelity.

Keywords


Multiframe, Image Restoration, Generative Adversarial Networks (GANs), Degradation Patterns, Fidelity.

References