Generating photo-realistic training data to improve face recognition accuracy

• Published in: Neural networks Vol. 134; pp. 86 - 94
• Main Authors: Sáez Trigueros, Daniel, Meng, Li, Hartnett, Margaret
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.02.2021
• Subjects: Automated Facial Recognition - methods; Face and gesture recognition; Facial Recognition - physiology; Generative adversarial learning; Humans; Image generation; Machine Learning; Neural Networks, Computer; Photography - methods; Generative adversarial learning; Face and gesture recognition; Image generation; Machine learning

Face recognition has become a widely adopted biometric in forensics, security and law enforcement thanks to the high accuracy achieved by systems based on convolutional neural networks (CNNs). However, to achieve good performance, CNNs need to be trained with very large datasets which are not always...