Missing Child Identification Using DLIB And Gan Based Facial Augmentation

This project presents a robust and intelligent system for identifying missing children using advanced facial recognition and object detection techniques. The proposed system is developed in three main stages. In the first stage, a dataset of children’s faces is collected and trained using the Haar Cascade Classifier with the default frontal face XML, allowing for basic face detection and recognition. The second stage enhances accuracy by integrating the YOLOv8 object detection model, which is trained on the same facial dataset to provide faster and more reliable face identification in real-time environments. To increase detection efficiency, especially when the uploaded image quality is low or outdated, the third stage includes an image augmentation module. This module generates multiple variants of the input image through transformations like rotation, scaling, and brightness adjustment. These augmented images are added to the training set, enabling the model to recognize faces under varied conditions. When a match is successfully identified, an automated email alert is sent to the concerned individual or authority using Flask-Mail integration. This system leverages the power of artificial intelligence and automation to support faster and more accurate identification of missing children, significantly aiding efforts in child recovery and public safety.