MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202521133920 A) filed by Sandip Institute Of Technology And Research Centre; Sandip Institute Of Engineering And Management; Sandip Polytechnic; Sandip Institute Of Pharmaceutical Sciences; Sandip University Nashik; and Sandip University Sijjoul on December 31, 2025, for An Automated System For Real-Time Age And Gender Detection.
Inventors include Kale, Sunil M.; Patil, Pramod; Vibhandik, Nivedita; Thoutam, Naresh; and Gaidhani, Abhay.
The application for the patent was published on July 31, 2026, under issue no. 31/2026.
Abstract: The present invention relates to an automated system for real-time age and gender detection using machine learning techniques. The system captures facial images or video frames and accurately predicts the gender and age group of individuals. It employs a dataset of annotated facial images, which undergo preprocessing including resizing, normalization, and augmentation to enhance model performance. Faces are detected using Haar cascade algorithms, while eye detection validates facial localization. Preprocessed facial regions are analyzed using a machine learning or deep learning classification module, such as convolutional neural networks, to determine age and gender. The system provides real-time outputs for applications in security surveillance, fraud prevention, criminal identification, identity verification, recruitment, retail analytics, and personalized services. The structured workflow follows the Waterfall Model, with design, implementation, testing, deployment, and maintenance phases. Performance is evaluated using standard metrics including accuracy, precision, recall, F1-score, mean absolute error, and ROC curves, ensuring reliable and robust predictions.
Disclaimer: Curated by HT Syndication.
