MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641086052 A) filed by Vallurupalli Nageswara Rao Vignana Jyothi Institute Of Engineering Technology on July 14, 2026, for Deep Learning-Based Sketch-To-Face Generation And Video Recognition System For Forensic Identification.
Inventors include Dr Nyemeesha V; A. Katyayani; Dr Para Rajesh; and M. Venkata Krishna Rao.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: In fields such as crime investigation and virtual effects, the ability to convert hand-drawn sketches into highly realistic human faces is a significant innovation. Our project leverages cutting-edge deep learning techniques, particularly Conditional Generative Adversarial Networks (CGANs) and image-to-image translation algorithms, to transform rough sketches into accurate, lifelike facial images. In a hybrid approach, these generated facial images are seamlessly integrated into video recognition systems to identify individuals in real- time footage. This dual functionality combining sketch-to-face generation with video-based face detection enhances forensic analysis, making the system particularly valuable for law enforcement and crime detection. The application incorporates advanced quantum- based optimizations, significantly boosting the performance and accuracy of face detection systems. Our innovative project represents a powerful tool in forensic science, providing law enforcement agencies with cutting-edge technology for identifying suspects from sketches and recognizing them in video footage, thereby improving the speed and precision of criminal investigations.
Disclaimer: Curated by HT Syndication.
