Abstract
Each year, a large number of youngsters are found missing in India. Among them, a large number of cases are never solved due to various difficulties faced by the police ranging from heavy paperwork to lacking technology. Therefore, one of this work’s key goals is to provide an application that may assist people whose children have been missing and rescued by the public. This will also reduce the time required to find the missing child to reunite the child with their loved ones as soon as possible. The pictures of child victims can be uploaded by the citizens along with landmarks, to our web app. The photographs will be matched to the missing child’s registered photographs if existing in the database. A deep neural network model is trained to locate the lost youngster using a facial picture uploaded by the citizens. Multi-Tasking CNN (MTCNN), the most efficient DNN technique for image-based apps, is used for facial Identification. The images were passed through an augmentation layer to get images of different orientations, brightness, and contrast, which were used ahead to train the EfficientNetB0 model. This model is then used to recognize faces in photographs. Using the MTCNN model for facial recognition with EfficientNetB0 and developing it yields a deep learning model that is free from all types of distortion. The model’s training accuracy is 96.66 percent and its testing accuracy is 76.81 percent, implying that there is approximately 77 percent possibility of finding a match for the missing kid. It was evaluated using 25 Child classes. Each Child class has around 15 to 20 images. These images are taken with different backgrounds and real-time settings so that model will work even when noise is present in the image.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have