Facial Image-Based Gender and Age Estimation

Abstract

The ability to automatically identify the age and gender of a customer from their facial image can significantly enhance the quality of customer service and improve business outcomes. This paper presents a deep learning-based approach for customer age and gender classification from facial images. The proposed method consists of a pre-processing step for face detection and alignment, followed by a deep convolutional neural network (CNN) that extracts features from the facial image and predicts the age and gender of the customer. The performance of the proposed method was evaluated on a public dataset, achieving high accuracy in both age and gender classification tasks. The results suggest that the proposed method has the potential to be applied in various business scenarios, such as personalized marketing, customer segmentation, and customer service improvement. Deployment of deep CNN models achieved state-ofthe-art performance. However, most of the CNN-based architectures are very complex with several dozens of training parameters so they require much computation time and resources. For this reason, we proposed a new CNN-based classification algorithm that has significantly small training parameters and time for training compared to existing methods. Despite having less complexity, our model showed better accuracy of age and gender classification on the UTKFace dataset.