• K.Shanmuka Venkat Sai
• N. Naveen Kumar

Facial attributes such as age and gender serve as fundamental elements in social interactions, rendering age and gender estimation from a single facial image a critical undertaking in various intelligent applications, including access control, human-computer interaction, law enforcement, marketing analytics, and visual surveillance. This study aims to develop an algorithm capable of accurately estimating the age and gender of individuals. Among the plethora of techniques available, the Haar cascade method stands out as one of the most widely utilized. In this research, we propose a novel model that leverages Haar Cascade to predict gender. The model is trained on a diverse dataset comprising male and female images, with positive and negative samples carefully curated. By extracting distinct facial features and employing the Haar Cascade classifier, our model determines whether the input image depicts a male or female individual. Furthermore, we integrate Deep Convolutional Neural Networks (CNNs) into our approach. CNNs exhibit remarkable efficacy, particularly in scenarios with limited data availability. For age approximation, we harness the power of the Caffe deep learning framework. Caffe boasts an expressive architecture and extensible codebase, making it a preferred choice for such tasks. Impressively, Caffe can process over 60 million photos per day, establishing itself as one of the fastest convolutional implementations accessible today.

Gender recognition, Age classification, Haar cascade, Caffe deep learning framework

"Unveiling Age and Gender: Deep Neural Network Insights", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.c28-c31, May-2024, Available :http://www.jetir.org/papers/JETIR2405204.pdf

"Unveiling Age and Gender: Deep Neural Network Insights", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppc28-c31, May-2024, Available at : http://www.jetir.org/papers/JETIR2405204.pdf