Transformation of Emotions in Images Using Poisson Blended Generative Adversarial Networks (Student Abstract)

Authors

  • Aristidis Dernelakis Johns Hopkins University Applied Physics Laboratory University of Maryland, Baltimore County
  • Jungin Kim Johns Hopkins University Applied Physics Laboratory Johns Hopkins University
  • Kevin Velasquez Johns Hopkins University Applied Physics Laboratory Johns Hopkins University
  • Lee Stearns Johns Hopkins University Applied Physics Laboratory

DOI:

https://doi.org/10.1609/aaai.v36i11.21603

Keywords:

Generative Adversarial Networks, Emotion Transformation, Unconstrained Images

Abstract

We propose a novel method for transforming the emotional content in an image to a specified target emotion. Existing techniques such as a single generative adversarial network (GAN) struggle to perform well on unconstrained images, especially when data is limited. Our method addresses this limitation by blending the outputs from two networks to better transform fine details (e.g., faces) while still operating on the broader styles of the full image. We demonstrate our method's potential through a proof-of-concept implementation.
AAAI-22 Proceedings Cover

Downloads

Published

2022-06-28

How to Cite

Dernelakis, A., Kim, J., Velasquez, K., & Stearns, L. (2022). Transformation of Emotions in Images Using Poisson Blended Generative Adversarial Networks (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12933-12934. https://doi.org/10.1609/aaai.v36i11.21603

Issue

Vol. 36 No. 11: IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations

Section

AAAI Student Abstract and Poster Program