Optimization enabled deep learning approach with probabilistic fusion for image inpainting

ABSTRACT

Nowadays, various deep learning (DL) approaches have been devised for image inpainting, which provided a substantial improvement in image quality. However, these approaches have failed to reconstruct the accurate structure of the original image. Hence, this research devised a novel and effective image inpainting approach, namely Autoregressive Flower Pollination Student Psychology Optimization (ArFPSPO). The image inpainting is carried out based on a newly devised hybrid context DL with the hybrid optimization scheme. The designed hybrid context DL approach adopts three DL techniques, such as Context encoder (CE), Context-Conditional Generative Adversarial Networks (CC-GAN), and Partial convolutional layer to complete the image inpainting process so that the outcomes are fused using probabilistic fusion with maximum entropy, thereby the final inpainted image is attained. Each of these three DL techniques is separately trained using a developed hybrid optimization technique. The experimental outcome reveals that the devised model gives optimal performance.

KEYWORDS:

• Conditional autoregressive value at risk
• context-conditional generative adversarial networks
• context encoder
• partial convolutional layer
• student psychology optimization
• deep learning
• Flower Pollination Student Psychology Optimization
• optimization

Disclosure statement

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

Data availability statement

Source code: https://www.transfernow.net/dl/20230501wHHH4rKf/2xiag64t.

Additional information

Notes on contributors

Kingsley S

Kingsley S was born in Chitharal, India, in 1985. He received the B.E. degree in computer science and engineering from Madha Engineering College, Chennai, India, in 2004, and the M.Tech in computer science and engineering from Easwari engineering college, Chennai, India, in 2011. In 2011, he joined the Department of Computer Science and Engineering, DMI College of Engineering as a Lecturer, and in 2012 became Assistant Professor. Since 2021 he has been with the department of Computer Science and Engineering, R.M.K Engineering College, Chennai. He is a doctoral candidate at Anna University in Chennai. He conducted research on image inpainting in ancient images using deep learning algorithms and has used several optimization techniques. He has been in this research for the past 7 years.

Sethukarasi T

Dr. Sethukarasi T is currently working as a Professor and Head in the department of Computer Science & Engineering, R.M.K. engineering College, Chennai, Tamil Nadu, India. She received her Ph.D., from the Faculty of Information & Communication Engineering, Anna University, Chennai, Tamil Nadu, India. Her area of research includes Data Mining, Soft Computing, Big data Analytics, Sensor Networks and Network Security. She has published more than 25 papers in the international journals and conferences. She is the recognized Research Supervisor of Anna University, Chennai and currently guiding 9 Ph.D scholars'. She produced 2 Ph.D., scholars. She is a life member in IAENG, IACSIT, IEI and STE.