Face aging with deep learning
| dc.contributor.author | Osama Arshad | |
| dc.contributor.author | Sharaz Haider | |
| dc.date.accessioned | 2026-01-28T15:21:09Z | |
| dc.date.available | 2026-01-28T15:21:09Z | |
| dc.date.issued | 2019 | |
| dc.description.abstract | Facial identity is primary method for identification of a human, facial feature of humans tends to change with aging. Predicting Facial changes with age progression (Face aging) is a challenging task. Recognizing face aging can be serve in various field including security, entertainment and cross age verification. A large number of missing children were found after long period of time, and were not been able to identified, also to identify criminal after the passage of time and it could be use in entertainment also. Currently face aging is done by using morphological techniques for example Face anthropometry and by using craniofacial growth model which usually results in generating fake images. Recent research showed that GAN (Generative Adversarial Network) produces the images with highly visual fidelity and have achieved great success. GAN based methodology provide automatic aging of faces. The deep generative networks have exhibited a remarkable capability in image generation. An approach for Identity-Preserving and GAN’s Latent vector optimization to generate more realistic images is introduced in this research. The dataset used for this research is MORPH and CACD to train our model of GAN as it requires a lot of data to learn. Moreover, an adversarial learning technique is presented to simultaneously train a generator and parallel discriminators, resulting in smooth continuous face aging sequences. The evaluation of objective of proposed method demonstrate the following results proposed framework produced more realistic results by comparing the state-of-art and ground truth. | |
| dc.identifier.uri | https://escholar.umt.edu.pk/handle/123456789/19131 | |
| dc.language.iso | en | |
| dc.publisher | UMT.Lahore | |
| dc.title | Face aging with deep learning | |
| dc.type | Thesis |