Age Invariant Face Recognition Using Convolutional Neural Networks and Set Distances

• 作者: Hachim El Khiyari Harry Wechsler
• 来源期刊: 信息安全(英文)
• 学科: 工学
• 关键词: Aging BIOMETRICS Convolutional Neural Networks (CNN) Deep LEARNING Image Set-Based Face Recognition (ISFR) Transfer LEARNING
• 年，卷（期）: 2017,（3）
• 页码范围: 174-185
• 页数: 12页
• 分类号: TP39

摘要

Biometric security systems based on facial characteristics face a challenging task due to variability in the intrapersonal facial appearance of subjects traced to factors such as pose, illumination, expression and aging. This paper innovates as it proposes a deep learning and set-based approach to face recognition subject to aging. The images for each subject taken at various times are treated as a single set, which is then compared to sets of images belonging to other subjects. Facial features are extracted using a convolutional neural network characteristic of deep learning. Our experimental results show that set-based recognition performs better than the singleton-based approach for both face identification and face verification. We also find that by using set-based recognition, it is easier to recognize older subjects from younger ones rather than younger subjects from older ones.