“AI-Based Criminal Sketch Generator for Suspect Identification"

The proposed CrimeVision AI system provides an intelligent and efficient solution for forensic facial sketch generation and criminal identification using deep learning techniques. The system successfully allows investigating officers and eyewitnesses to provide facial features of suspects and generate realistic forensic sketches through AI-based processing. The integration of Generative Adversarial Networks (GANs) improves the quality, accuracy, and realism of generated facial outputs. The developed platform combines frontend technologies, backend services, database management, and artificial intelligence into a centralized investigation system. The React.js frontend provides a user-friendly interface, while Spring Boot and PostgreSQL ensure secure data handling, efficient record management, and reliable communication between system modules. The proposed system reduces the dependency on manual sketch artists and minimizes investigation delays by automating the sketch generation process. It also improves suspect identification efficiency through organized criminal record management and intelligent result analysis. . Overall, the project demonstrates the practical application of artificial intelligence and deep learning technologies in modern forensic science and law enforcement operations. The system provides a scalable, reliable, and technology-driven approach for improving criminal investigation procedures and digital forensic analysis.

1.    Jain, A.K.; Bolle, R.; Pankanti, S. Biometrics: Personal Identification in Networked Society; Springer: Berlin/Heidelberg, Germany, 2006; Volume 479. 2.    Facial Identification Scientific Working Group. Facial Image Comparison Feature List for Morphological Analysis, Version 2.0, 2018. Available online: https://fiswg.org/FISWG_Morph_Analysis_Feat ure_List_v2.0_20180911.pdf (accessed on 20 May 2024). 3.    Richmond, S.; Howe, L.J.; Lewis, S.; Stergiakouli, E.; Zhurov, A. Facial genetics: A brief overview. Front. Genet. 2018, 9, 462. [CrossRef] [PubMed] 4.    Ouyang, S.; Hospedales, T.M.; Song, Y.Z.; Li, X. ForgetMeNot: Memory-Aware Forensic Facial Sketch Matching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016. 5.    Frowd, C.D.; Carson, D.; Ness, H.; McQuiston-Surrett, D.; Richardson, J.; Baldwin, H.; Hancock, P. Contemporary composite techniques: The impact of a forensically- relevant target delay. Leg. Criminol. Psychol. 2005, 10, 63–81. [CrossRef] 6.    Faces Software. Facial Composite Software. Available online: https://facialcomposites.com/ (accessed on 10 June 2024). 7.    FACETTEFace Design System— Phantombild-Programm—Facial Composites. Available online: http://www.facette.com/index. php?id=1&L=1 (accessed on 10 June 2024). 8.    Singular Inversions. 2024. FaceGen 3D. Available online: https://facegen.com/3dprint.htm (accessed on 10 June 2024). 9.    Lugmayr, A.; Danelljan, M.; Romero, A.; Yu, F.; Timofte, R.; Van Gool, L. Repaint: Inpainting using denoising diffusion probabilistic models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 11461–11471. 10. 10.  Cheng, Y.C.; Lin, C.H.; Lee, H.Y.; Ren, J.; Tulyakov, S.; Yang, M.H. Inout: Diverse image outpainting via GAN inversion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 11431–11440.