header
Image from OpenLibrary

Gankin: generating kin faces using Disentangled gan / Fady Saad Said Ghatas ; Supervised Magda Fayek , Elsayed Hemayed , Mayada Hadhoud

By: Contributor(s): Material type: TextTextLanguage: English Publication details: Cairo : Fady Saad Said Ghatas , 2020Description: 70 P . : charts , facsmilies ; 25cmOther title:
  • توليد وجوة الأبناء عن طريق فصل الخواص فى شبكة الخصومة التوليدية [Added title page title]
Subject(s): Available additional physical forms:
  • Issued also as CD
Dissertation note: Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Computer Engineering Summary: Kin image generation from parents{u2019} images is a high-level prediction and generation problem. This study presents a new method to predict and generate a kin face using parents{u2019} faces, i.e. Tri-subject prediction or two-to-one prediction. We use a pipeline of unconditional GANs to overcome mode-collapse in conditional GANs. The model achieves promising results compared to the state-of-the-art, our model achieves a retrieval score of 0.19 versus 0.107 by the state-of-the-art. Our model is validated against SelfKin kinship verification model and achieved an accuracy of (63 % 7 %)
Tags from this library: No tags from this library for this title. Log in to add tags.
Star ratings
    Average rating: 0.0 (0 votes)
Holdings
Item type Current library Home library Call number Copy number Status Date due Barcode
Thesis Thesis قاعة الرسائل الجامعية - الدور الاول المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.06.M.Sc.2020.Fa.G (Browse shelf(Opens below)) Not for loan 01010110081985000
CD - Rom CD - Rom مخـــزن الرســائل الجـــامعية - البدروم المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.06.M.Sc.2020.Fa.G (Browse shelf(Opens below)) 81985.CD Not for loan 01020110081985000

Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Computer Engineering

Kin image generation from parents{u2019} images is a high-level prediction and generation problem. This study presents a new method to predict and generate a kin face using parents{u2019} faces, i.e. Tri-subject prediction or two-to-one prediction. We use a pipeline of unconditional GANs to overcome mode-collapse in conditional GANs. The model achieves promising results compared to the state-of-the-art, our model achieves a retrieval score of 0.19 versus 0.107 by the state-of-the-art. Our model is validated against SelfKin kinship verification model and achieved an accuracy of (63 % 7 %)

Issued also as CD

There are no comments on this title.

to post a comment.