An Improved Technique for Face Age Progression and Enhanced Super-Resolution with Generative Adversarial Networks
- PDF / 3,435,478 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 108 Downloads / 243 Views
An Improved Technique for Face Age Progression and Enhanced Super‑Resolution with Generative Adversarial Networks Neha Sharma1 · Reecha Sharma1 · Neeru Jindal2
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Several techniques are available for face age progression still identity preservation as well age estimation accuracy are big challenges and need attention. So, the proposed work is focused on these key issues using Generative Adversarial Networks (GANs). To produce a realistic appearance with an enhanced vision of face image, a fusion-based Generative Adversarial Network approach is used. GAN has a generator and a discriminator network. The generator produces fake images which are further differentiated by discriminator whether the image is real or fake. Initially, Cycle-Generative Adversarial Network (CycleGAN) achieves the face age progression, further Enhanced Super-resolution Generative Adversarial Network (ESRGAN) automatically enhance the aged face image to improve the visibility. Simulation results on five face datasets, namely IMDB-WIKI, CACD and UTKFace, FGNET, Celeb A are evaluated. The proposed work efficacy is observed in comparison to previous techniques using a quantitative Face ++ research toolkit with parameters confidence score number and age estimation value. It is observed that the proposed work produces the aged face precisely with an error rate of 0.001%, with a a confidence score 95.13 to 95.39 on datasets. Keywords Face age progression · Generative adversarial network · Enhanced superresolution · Age estimation
* Neha Sharma [email protected] Reecha Sharma [email protected] Neeru Jindal [email protected] 1
Department of Electronics and Communication Engineering, Punjabi University, Patiala, Punjab 147001, India
2
Department of Electronics and Communication Engineering, Thapar Institute of Engineering and Technology, Patiala, Punjab 147001, India
13
Vol.:(0123456789)
N. Sharma et al.
1 Introduction Face age progression along with super-resolution is a continuous research domain in the computer vision field because of its significant applications nowadays. In the real world, there are numerous cases present in which authorities are in search of missing human beings. For instance, in many cases of law enforcement, the appearance and age of the suspected person are essential and often the previous photographs are the only clue available [1]. Moreover, compared to low-resolution images, the high-resolution images provide rich information. Although, forensic artists attempt to attain the age progress on the face image of an individual person whose results depend on the individual’s state of mind and expertise attempting age progression. In a field of computer vision, computeraided face aging (also called face age progression and age synthesis) [2–5], the goal is to provide specific age of the face image with natural aging. In the past few years, remarkable progress is achieved on age progression using various techniques [6–8]. Age prog
Data Loading...
