DECODING THE VEILED FACE DETECTION AND IDENTIFICATION USING DEEP LEARNING

Abstract

In today's rapidly evolving world, where technology is progressing swiftly, there is an increasing demand for facial recognition systems. These technologies are similar to digital forensics in that they can recognize people by scanning their faces. However, one key problem they confront is dealing with covered or occluded faces, which might restrict their accuracy and efficacy in real-world situations. To overcome this issue, created a system that is capable of identifying individuals even when their faces are veiled. We used the face detector algorithm called MTCNN for face detection with 99.8% accuracy. Further we have conducted feature extraction and pre-processing our self-created dataset. Our project utilizes the power of deep learning model: ResNet50, the form of deep neural network architectures well-suited for the job of features extraction. These features are matched by using Cosine similarity with accuracy of 92%. By leveraging the capabilities in the deep learning algorithms along with computer vision techniques, this project is able to provide a robust solution for automating the recognition of partially occluded faces. This enhancement in facial recognition technologies is required for accurate results and transparency in the end product. We aim to increase the system's ability to recognize people effectively in real- world circumstances by training it on an extensive dataset containing photos of faces with varying degrees of occlusion. We hope to contribute to the improvement of the practicality and reliability of facial recognition technology, which has potential applications in safety, agencies that required strong safety, and other domains where accurate identification is required