Image noise removal using optimal deep learning-based noisy pixel identification and image enhancement

ABSTRACT

Image restoration is utilised to discard image noise without demolishing edge information. A new optimisation based deep model is devised for image enhancement with restoration. Here, the noisy pixel map is detected with Deep Residual Network (DRN). DRN training is carried out using the JayaBat algorithm, which was created by combining the Jaya optimisation method and the Bat algorithm (BA). The statistical model is then used to restore the noisy pixels. The neuro fuzzy model and the Image Enhancement Conditional Generative Adversarial Network (IE-CGAN) are taken into account while enhancing images. Here, the IE-CGAN training is performed with designed CAViaRJayaBat. The CAViaRJayaBat is designed newly by combining the CAViaR and JayaBat algorithms. The proposed CAViaRJayaBat-based IE-CGAN offered improved performance with the best Peak signal to noise ratio (PSNR) of 49.049 dB, the highest Second derivative measure of enhancement (SDME), 62.570 dB, and the highest structural similarity index (SSIM), 0.858.

KEYWORDS:

• Image restoration
• image enhancement
• noisy pixel identification
• neuro fuzzy system
• deep residual network
• JayaBat algorithm
• image enhancement conditional generative adversarial network
• second derivative measure of enhancement

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

S.P. Premnath

Dr. S. P. Premnath, Completed his doctorate degree in 2022 from Anna University in Information and Communication Engineering and at present he is working as an Assistant Professor in the department of Electronics and Communication Engineering in Sri Krishna College of Engineering and Technology, Coimbatore, Tamilnadu, India. He has obtained his Master's Degree in Communication System from S.A college of Engineering, Chennai, (Anna University). He has done extensive research experience in Wireless Communication and Image Processing. He has also participated in many conferences and published several papers in National and International Journals.

J. Arokia Renjith

Dr. J. Arokia Renjith, B.E, M.E., Ph.D., works as the Professor and Head of the CSE Department of Jeppiaar Engineering College, Chennai, Tamil Nadu, India. He has more than 20 years of teaching experience, and his areas of specialization are Image Processing, Data Mining, Cloud Computing, Artificial Intelligence. He had published more than 50 research papers in reputed National and International journals and in the proceedings of National and International level Conferences. He has taught various subjects in Computer Science and Engineering department. He has produced two PhD Doctorates and currently acting as Research Supervisor for eight PhD research scholars. He has guided more than 30 student projects in undergraduate level and postgraduate level.

J. P. Ananth

Dr. J. P. Ananth received his B.E (2000) and M.E (2005) in Computer Science and Engineering from M S University and Ph.D (2012) from Sathyabama University, Chennai. He is a Senior member of IEEE and a member of IEEE Computer Society. Having 20 years of teaching experience, presently he is working as a Professor in the School of Computer Science and Engineering, Sri Krishna College of Engineering and Technology, Coimbatore. His research interests include Computer Vision, Pattern Recognition, Artificial Itelligence and Data Analytics. His work has been documented in many journals including IET Image Processing, The Computer Journal, Wireless Networks-Springer. He serves as a reviewer for several International Conferences and Journals including IEEE Access and a member of technical and executive committees for International Conferences.