Generative AI-Assisted Face Synthesis for Forensic and Criminal Investigations

DOI

10.2991/978-94-6239-644-9_10How to use a DOI?

Keywords

Face Recognition; Face Synthesis; Generative AI; Generative Adversarial Networks; Image-to-Image Translation

Abstract

Forensic investigations frequently rely on facial sketches to identify individuals involved in criminal activities. However, since the human face is so diverse and variable, it is tough to predict the person from a forensic sketch expert’s sketch as they often lack realism and can be influenced by eyewitness biases. Recent advancements in generative AI, particularly Gen- erative Adversarial Networks (GANs) have revolutionized image synthesis, enabling the generation of highly realistic facial images from sketches. Hence, we aim to leverage this technology and make this process more efficient and foolproof using GANs. In this paper, we propose advancements to existing technology by using a combination of PatchGAN discriminator and a U-Net generator.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shraddha Pandey
AU  - Ishaan Shankar Bansal
AU  - Noel Jeygar Robert
PY  - 2026
DA  - 2026/04/19
TI  - Generative AI-Assisted Face Synthesis for Forensic and Criminal Investigations
BT  - Proceedings of the Global Innovation and Technology Summit “AAROHAN 3.0”_Engineering track (GITS-EAS 2025)
PB  - Atlantis Press
SP  - 126
EP  - 136
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-644-9_10
DO  - 10.2991/978-94-6239-644-9_10
ID  - Pandey2026
ER  -