Noisy image classification using hybrid deep learning methods

• Main Authors: Roy, Sudipta Singha, Ahmed, Mahtab, Akhand, Muhammad Aminul Haque
• Format: Article
• Language: English
• Published: Universiti Utara Malaysia Press 2018
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://repo.uum.edu.my/24025/1/JICT%20%2018%202%202018%20233%E2%80%93269.pdf; http://repo.uum.edu.my/24025/; http://jict.uum.edu.my/index.php/current-issues#A4
• Institution: Universiti Utara Malaysia

In real-world scenario, image classification models degrade in performance as the images are corrupted with noise, while these models are trained with preprocessed data. Although deep neural networks (DNNs) are found efficient for image classification due to their deep layer-wise design to emulate l...