A novel Facial Recognition technique with Focusing on Masked Faces

2025-01-08

AI Summary

To address the significant performance degradation of face recognition systems under facial mask occlusion, this paper introduces the cross-state face matching task—Masked-Unmasked Face Matching (MUFM)—aiming to achieve robust identity matching between masked and unmasked facial appearances of the same individual. Methodologically, we propose the first adoption of cosine similarity as the core similarity metric for MUFM, coupled with a VGG16-based transfer learning framework for feature extraction and a k-nearest neighbors (k-NN) classifier. The model is trained and evaluated on a multi-source, real-world paired dataset comprising authentic masked–unmasked face pairs. Experimental results demonstrate that the proposed MUFM model achieves substantial improvements in recognition accuracy under mask occlusion, effectively mitigating the performance deterioration caused by partial facial occlusion in conventional systems. This work delivers a deployable, robust identity verification solution applicable to security, healthcare, and public surveillance scenarios.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Recognizing the same faces with and without masks is important for ensuring consistent identification in security, access control, and public safety. This capability is crucial in scenarios like law enforcement, healthcare, and surveillance, where accurate recognition must be maintained despite facial occlusion. This research focuses on the challenge of recognizing the same faces with and without masks by employing cosine similarity as the primary technique. With the increased use of masks, traditional facial recognition systems face significant accuracy issues, making it crucial to develop methods that can reliably identify individuals in masked conditions. For that reason, this study proposed Masked-Unmasked Face Matching Model (MUFM). This model employs transfer learning using the Visual Geometry Group (VGG16) model to extract significant facial features, which are subsequently classified utilizing the K-Nearest Neighbors (K-NN) algorithm. The cosine similarity metric is employed to compare masked and unmasked faces of the same individuals. This approach represents a novel contribution, as the task of recognizing the same individual with and without a mask using cosine similarity has not been previously addressed. By integrating these advanced methodologies, the research demonstrates effective identification of individuals despite the presence of masks, addressing a significant limitation in traditional systems. Using data is another essential part of this work, by collecting and preparing an image dataset from three different sources especially some of those data are real provided a comprehensive power of this research. The image dataset used were already collected in three different datasets of masked and unmasked for the same faces.

Problem

• Facial Recognition
• Mask-Wearing
• Accuracy Degradation

Innovation

• MUFM Model
• Cosine Similarity
• Masked Facial Recognition