scholarly journals Temporal Non-volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition

2017 ◽  
Author(s):  
Chi Nhan Duong ◽  
Kha Gia Quach ◽  
Khoa Luu ◽  
T. Hoang Ngan Le ◽  
Marios Savvides
Keyword(s):  
Face Recognition ◽  
Age Progression ◽  
Volume Preserving ◽  
Facial Age

scholarly journals Extreme Learning Machine-Based Age-Invariant Face Recognition With Deep Convolutional Descriptors

2022 ◽  
Vol 13 (1) ◽  
pp. 1-18
Author(s):  
Leila Boussaad ◽  
Aldjia Boucetta
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
Extreme Learning Machine ◽  
Hypothesis Test ◽  
Deep Convolutional Neural Networks ◽  
Age Progression ◽  
Learning Machine ◽  
Elm Classifier ◽  
Fully Connected ◽  
Accuracy Rates

The principal intention of this paper is to study face recognition across age progression at two levels: feature extraction and classification. In other words, this work aims to prove the benefit of replacing the Softmax layer of the Deep-Convolutional Neural Networks (CNN) by Extreme Learning Machine (ELM) classifier based on deep features computed from fully-connected layer of pre-trained AlexNet CNN model, in a context of age-invariant face recognition. Experimental results indicate that the ELM classifier combined with feature extracted by the pre-trained AlexNet CNN model worked effectively for face recognition across age progression. As significant highest mean accuracy rates are always obtained using ELM classifier. These results are more significant, following a 95% confidence level hypothesis test.

Effects of Facial Identity on Age Judgments

2010 ◽  
Vol 57 (5) ◽  
pp. 390-397 ◽  
Author(s):  
Yuly Dagovitch ◽  
Tzvi Ganel
Keyword(s):  
Face Recognition ◽  
Repetition Priming ◽  
Experimental Session ◽  
Priming Effects ◽  
Facial Identity ◽  
Priming Paradigm ◽  
Memory Representations ◽  
The Relationship ◽  
Unfamiliar Faces ◽  
Facial Age

According to current face recognition models, facial identity is processed independently from other visually derived facial aspects, such as facial age. Here we used a repetition priming paradigm to investigate the relationship between the processing of facial identity and facial age. In Experiment 1, participants made speeded age classifications for primed and unprimed faces of famous celebrities. Performance was faster and more accurate for primed compared to unprimed faces, which indicates that the processing of facial age benefits from priming effects. In Experiment 2, priming was also found for preexperimentally unfamiliar faces which were familiarized during the experimental session. In Experiment 3, priming effects were found even when different photos of the same people were presented at study and at test. These results suggest that the processing of age is mediated by memory representations of facial identity.

Sign in / Sign up

Export Citation Format

Share Document