Tracing the Missing person using Artificial Intelligence

Information Technology

Uncountable numbers of reported missing children in India occur each year. A significant portion of missing children have not been found. In this work, face recognition is used in a novel way to identify the reported missing child from the large number of child photographs that are accessible. The general public is able to post images of children that appear suspicious along with descriptions of nearby landmarks. The image will automatically be compared to the recorded images contained in the database are those of the lost child. The missing child database photo that most closely resembles the input child image is selected after categorizing the input child image. Using a facial image supplied by the public, a deep learning model is trained to accurately identify the missing child from the missing child image database. Face recognition is done using Convolutional Neural Networks (CNN), a relatively efficient deep learning technique for image-based applications. Using the VGG-Face deep architecture pre-trained CNN model, face descriptors are derived from the images. Our technique uses convolution networks only as high-level feature extractors, as opposed to typical deep learning applications, and the trained KNN classifier performs the child recognition. By selecting and appropriately training the top CNN model for face recognition, VGG-Face, A deep learning model that is resistant to noise, lighting, contrast, occlusion, image pose, and child age is what we are able to achieve. This model outperforms earlier approaches in the identification of missing children based on face recognition

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.