Academic Journal of Computing & Information Science, 2024, 7(5); doi: 10.25236/AJCIS.2024.070517.
Yaohui Wang
Petroleum School, China University of Petroleum-Beijing at Karamay, Karamay, 834000, China
With the rapid advancement of computer vision and artificial intelligence, facial age estimation has become an important area of research and application in various fields such as preventing adolescent gaming addiction, identity verification, and target advertising. Existing methods primarily suffer from sensitivity to dataset biases, limited applicability, and shallow neural network depths. Addressing these issues, this paper propose an innovative approach based on convolutional neural networks, namely Age-InceptionNet. Drawing upon the excellent structure of GoogLeNet, this method optimizes data preprocessing, feature extraction, fusion, and age prediction regression, thereby enhancing the accuracy and robustness of the model. Experimental results demonstrate that Age-InceptionNet achieves favorable outcomes with a Mean Absolute Error of 3.33 on the Morph-II dataset. This paper provides a new solution for age estimation, improving model performance and contributing to further advancements in this field.
Age Estimation, Convolutional Neural Network (CNN), Feature Extraction, Feature Fusion
Yaohui Wang. Age-InceptionNet: A Deeper and More Robust Facial Age Prediction Model. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 5: 130-135. https://doi.org/10.25236/AJCIS.2024.070517.
[1] Shou Y, Meng T, Ai W, et al. A comprehensive survey on multi-modal conversational emotion recognition with deep learning[J]. arXiv preprint arXiv:2312.05735, 2023.
[2] Shou Y, Cao X, Meng D. Masked Contrastive Graph Representation Learning for Age Estimation[J]. arXiv preprint arXiv:2306.17798, 2023.
[3] Meng T, Shou Y, Ai W, et al. A multi-message passing framework based on heterogeneous graphs in conversational emotion recognition[J]. Neurocomputing, 2024, 569: 127109.
[4] Meng T, Shou Y, Ai W, et al. Deep imbalanced learning for multimodal emotion recognition in conversations [J]. arXiv preprint arXiv:2312.06337, 2023.
[5] Shou Y, Cao X, Meng D, et al. A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognition [J]. arXiv preprint arXiv:2306.17799, 2023.
[6] Shou Y, Ai W, Meng T. Graph information bottleneck for remote sensing segmentation[J]. arXiv preprint arXiv:2312.02545, 2023.
[7] Edmonds, Emily, C. Cognitive Mechanisms of False Facial Recognition in Older Adults.[J]. Psychology & Aging, 2012.DOI:10.1037/a0024582.
[8] Shou Y, Ai W, Meng T, et al. Czl-ciae: Clip-driven zero-shot learning for correcting inverse age estimation [J]. arXiv preprint arXiv:2312.01758, 2023.
[9] Ai W, Shou Y, Meng T, et al. Der-gcn: Dialogue and event relation-aware graph convolutional neural network for multimodal dialogue emotion recognition[J]. arXiv preprint arXiv:2312.10579, 2023.
[10] Shou Y, Meng T, Ai W, et al. Adversarial representation with intra-modal and inter-modal graph contrastive learning for multimodal emotion recognition[J]. arXiv preprint arXiv:2312.16778, 2023.
[11] Shou Y, Meng T, Ai W, et al. Conversational emotion recognition studies based on graph convolutional neural networks and a dependent syntactic analysis[J]. Neurocomputing, 2022, 501: 629-639.