Face reconstruction with generative adversarial network

Dino Hariatma Putra, T. Basaruddin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Generative Adversarial Network (GAN) is a framework of deep learning in generative models. The generative model aims to synthesize a new data so that it has a distribution of distribution according to the original data distribution. In the current development, GAN is not only used to synthesize data from noise alone, but in the current development it has begun to be used to translate data from a domain to data with a different domain. Several studies have been developed, such as CycleGAN, and Pix2pix. In this study, the face has not been used as an object of translation. In this study a model for translating images of face sketches into face images will be made.

Original languageEnglish
Title of host publicationICMLSC 2019 - Proceedings of the 3rd International Conference on Machine Learning and Soft Computing
PublisherAssociation for Computing Machinery
Pages181-185
Number of pages5
ISBN (Electronic)9781450366120
DOIs
Publication statusPublished - 25 Jan 2019
Event3rd International Conference on Machine Learning and Soft Computing, ICMLSC 2019 - Da Lat, Viet Nam
Duration: 25 Jan 201928 Jan 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference3rd International Conference on Machine Learning and Soft Computing, ICMLSC 2019
Country/TerritoryViet Nam
CityDa Lat
Period25/01/1928/01/19

Keywords

  • CycleGAN
  • Deep learning
  • Face image
  • Face sketch
  • Generative adversarial network
  • Synthesize
  • Translation

Fingerprint

Dive into the research topics of 'Face reconstruction with generative adversarial network'. Together they form a unique fingerprint.

Cite this