Skip to main navigation Skip to search Skip to main content

Human Sketch Recognition using Generative Adversarial Networks and One-Shot Learning

  • Deepanshu Wadhwa
  • , Utkarsh Maharana
  • , Devina Shah
  • , Vaibhav Yadav
  • , Prashant Pandey

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

2 Scopus citations

Abstract

We introduce a model for face recognition from sketches. The system follows a multi-layered approach and is built by combining sketch to image generation, and face recognition methods. First, sketch to photo generation is achieved by employing cGAN based pix2pix model. Then face recognition is done by One Shot Learning using FaceNet. The sketch recognition model developed through this research is able to yield good results on multiple datasets with the generated images performing with an accuracy close to that with the original images. The average difference from the recognition accuracy as compared to with original images was approximately three percent on the datasets used. Real time recognition using sketches as inputs is also effectively explored through the combination of these two layers of approach.

Original languageEnglish
Title of host publication2019 12th International Conference on Contemporary Computing, IC3 2019
EditorsSundaraja Sitharama Iyengar, Vikas Saxena
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728135915
DOIs
StatePublished - Aug 2019
Event12th International Conference on Contemporary Computing, IC3 2019 - Noida, India
Duration: Aug 8 2019Aug 10 2019

Publication series

Name2019 12th International Conference on Contemporary Computing, IC3 2019

Conference

Conference12th International Conference on Contemporary Computing, IC3 2019
Country/TerritoryIndia
CityNoida
Period08/8/1908/10/19

Keywords

  • conditional generative adversarial network
  • generative adversarial networks
  • one shot learning
  • sketch recognition
  • sketch to image generation

Fingerprint

Dive into the research topics of 'Human Sketch Recognition using Generative Adversarial Networks and One-Shot Learning'. Together they form a unique fingerprint.

Cite this