Effect of subject's age and gender on face recognition results

• Published in: Journal of visual communication and image representation Vol. 60; pp. 116 - 122
• Main Authors: wu, Shifeng, Wang, Dahu
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.04.2019
• Subjects: Age; Deep learning; Face recognition; Gender; Deep learning; Gender; Face recognition; Age
• ISSN: 1047-3203; 1095-9076
• DOI: 10.1016/j.jvcir.2019.01.013

Nowadays, more and more places need authentication. Face recognition is a mature technology for identity verification research. Recognition accuracy is an important indicator for evaluating authentication algorithms. In order to improve the accuracy of identity verification, advanced face is used. Feature recognition algorithm is an effective way, but it is also an effective algorithm to study the factors affecting facial features. Therefore, many researchers study the recognition results based on the poses of the face, light and other factors. This paper is also a study on the factors affecting face recognition, mainly by studying the influence of the age and gender factors on the identity verification results, and using the deep learning method to classify facial features. The simulation results show that the average recognition rate reaches 83.73%. At the same time, this paper analyzes the effect of age and gender on the classification results. The results show that the recognition effect of middle-aged men in male subjects is lower than that of youth and the elderly. Women have little difference in recognition effect with age. Males have higher recognition rates than women.