ACNN-Based Framework for Locating Missing Persons Through Advanced Face Recognition Techniques

Every year, cops across India file thousands of missing person cases, yet many remain untraceable, mainly because there is no intelligent, unifying system of identification to deal with the issue. To address this critical challenge, we propose a novel framework, Missing Persons Identification by Advanced Recognition of Faces (MPIARF), which utilizes an ACNN. Incorporating a Convolutional Neural Network (CNN), such as DeepFace or VGG16, this deep approach to human identification is fast, agile, and generally improves identification performance. Input images are classified into age and gender using CNNs, and with the help of DeepFace, highly detailed features for faces are extracted using the VGG16 model. A list of features is generated and compared to a database of known individuals in real-time using a cosine similarity metric. The framework is tailored to manage issues such as temporal variation in facial appearance, ensuring resilient long-distance identification. The system instantly reports possible matches to the authorities or organizations. The solution is tailored for edge deployment, utilizing Flask and TensorFlow Lite to provide a lightweight interface that ensures portability and real-time monitoring. Our comprehensive, scalable approach significantly enhances the speed, Accuracy, and usability, delivering real societal and humanitarian value.