Procedia Computer Science · 2024 · 37 citations · 21 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDeep LearningFace RecognitionFacial ExpressionImage Feature EngineeringRepresentation LearningSex EstimationAge Group ClassificationAge RecognitionConvolutional Neural NetworksData AugmentationDeep Learning-based ClassificationFacial Expression AnalysisGender Perception From Facial AppearanceTraining
Human age and gender prediction from facial images has garnered significant attention due to its importance in various applications. Traditional models struggle with large-scale variations in unfiltered images. Convolutional Neural Networks (CNNs) have emerged as effective tools for facial analysis due to their robust performance. This paper presents a novel CNN approach for robust age and gender classification using unconstrained real-world images. The CNN architecture includes convolution, pooling, and fully connected layers for feature extraction, dimension reduction, and mapping to output classes. Adience and UTKFace datasets were utilized, with the best training and testing accuracies achieved using an 80% training and 20% testing data split. Robust image pre-processing and data augmentation techniques were applied to handle dataset variations. The proposed approach outperformed existing methods, achieving age prediction accuracies of 86.42% and 81.96%, and gender prediction accuracies of 97.65% and 96.32% on the Adience and UTKFace datasets, respectively.
21
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Age Progression/Regression by Conditional Adversarial Autoencoder
Zhifei Zhang, Yang Song, Hairong Qi · 2017 · 1.1K citations
Computing, Computer Science, Aging +14
A hybrid deep learning CNN–ELM for age and gender classification
Mingxing Duan, Kenli Li, Canqun Yang et al. · Neurocomputing · 2017 · 257 citations