Prediction of Human Age and Gender Using Deep Learning For Smart Security Systems

The demand for accurate identification and verification of a person has increased as the number of smart security systems has grown. In recent years, data from a human face has been used in numerous real-world applications, including social networking, security monitoring, advertising, and entertainment. Computer vision researchers have long been interested in this topic because automatic age and gender prediction from facial images is crucial for interpersonal communication. This work predicts that the gender will be either ‘Male’ or ‘Female,’ and that the age will be one of the following ranges: (0-5), (6-10), (11-17), (18-25), (25-32), (33-45), (46-55), (55-70). In the proposed system the images are preprocessed and then the convolutional neural networks are used to extract age and gender-related features and classified the images using the appropriate classifiers. The face images are taken from the UTK dataset and the proposed method achieved a training accuracy of 92.5% and a validation accuracy of 90%.