Since the rise in social media and interactive systems in recent decades, the automatic classification of age and gender has become relevant to most of the social platforms and human-computer interactions. To achieve this task, many methods are implemented, but somehow those are not effective with real-world images as most of the models are trained using images of limited dataset taken from lab settings which are generally constrained in nature. Such images do not contain variations of appearance which are usually observed in images of the real world such as social networks, online repositories, and websites. In this paper, we try to improve the performance by making use of the deep convolutional neural network (CNN). The proposed network architecture uses Adience benchmark for gender as well as age estimation and its performance are much better with real-world images of the face. Here in this paper, a suitable method is described for the detection of a face at real-time and estimation of their age and gender. It first detects whether a face is there or not in the image captured. If it is present, the face is detected and the region of face content is returned using colored square structure and returns their age and gender as a result. The convenient and easy hardware implementation for this method is by utilizing a Raspberry-Pi kit and camera, as it is a minicomputer of credit card size. To build an effective age and gender estimator, the concept of Deep Convolution Neural Network is used. The input data contains different age groups of male and female face images. Over captured faces’ feature extraction are compared with this input data to evaluate the age as well as the gender of the person.

Raspberry Pi, Human face detection, OpenCV, Age, and Gender detection, Convolutional Neural Network

[1]. Anusha, A. V., J. K. Jayasree, Anusree Bhaskar, and R. P. Aneesh, "Facial expression recognition and gender classification using facial patches," In 2016 International Conference on Communication Systems and Networks (ComNet), pp. 200-204, IEEE, 2016.
[2]. Geng, Xin, Zhi-Hua Zhou, and Kate Smith-Miles, "Automatic age estimation based on facial aging patterns," IEEE Transactions on pattern analysis and machine intelligence 29, no. 12 (2007), pp. 2234-2240, 2007.
[3]. Sethuram, Amrutha, Jason Saragih, Karl Ricanek, and Benjamin Barbour, "Extremely dense face registration: Comparing automatic landmarking algorithms for general and ethno-gender models," In 2012 IEEE Fifth International Conference on Biometrics: Theory, Applications, and Systems (BTAS), pp. 135-142, IEEE, 2012.
[4]. Da`San, Mohammad, Amin Alqudah, and Olivier Debeir, "Face detection using Viola and Jones method and neural networks," In 2015 International Conference on Information and Communication Technology Research (ICTRC), pp. 40-43, IEEE, 2015.
[5]. Angus, Alvin Titus R., John Alvin P. Guillen, Maurice Laurence G. Lenon, Ray Justin C. Principe, Gerald P. Feudo, and Kanny Krizzy D. Serrano, "A clustering system utilizing acquired age and gender demographics thru facial detection and recognition technology," In 2017 IEEE 9th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM), pp. 1-6, IEEE, 2017.
[6]. Gauswami, Mitulgiri H., and Kiran R. Trivedi, "Implementation of machine learning for gender detection using CNN on the raspberry Pi platform," In 2018 2nd International Conference on Inventive Systems and Control (ICISC), pp. 608-613, IEEE, 2018.
[7]. Liu, Xuan, Junbao Li, Cong Hu, and Jeng-Shyang Pan, "Deep convolutional neural networks-based age and gender classification with facial images," In 2017 First International Conference on Electronics Instrumentation & Information Systems (EIIS), pp. 1-4. IEEE, 2017.
[8]. Aishwarya Admane, Afrin Sheikh, Sneha Paunikar, Shruti Jawade, Shubhangi Wadbude, Prof. M. J. Sawarkar , "A Review on Different Face Recognition Techniques", International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), ISSN : 2456-3307, Volume 5 Issue 1, pp. 207-213, January-February 2019.
[9]. A. K. Gupta, S. Gupta, “Neural Network through Face Recognition”, International Journal of Scientific Research in Computer Science and Engineering Vol.6, Issue.2, pp.38-40, April (2018) E-ISSN: 2320-7639.