Skip to main content
SpringerLink
Log in

Age Detection in a Surveillance Video Using Deep Learning Technique

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

The video streams that are collected from CCTV surveillance camera can be used in many applications such as crowd analysis, forensic, self-profile analysis, and social network user’s analysis. Soft biometrics such as age, gender, height, skin color can be used for human analysis. This requires object detection and feature analysis. Works reported for face recognition and age detection have poor performance with real-world profile images. It may be because of incomplete description of the human object. Also, they rely on traditional image processing algorithms that extract hand-crafted features. Deep learning workflow transforms the identified patterns into mathematical modeling that can be used for subsequent prediction. Residual networks can skip connections and can address vanishing gradient problem with improved accuracy. Wide ResNet 34-based system is proposed in this paper that automatically predicts age of human object in video images. Modified Wide ResNet is used for feature extraction that learns facial keypoints, image reconstruction using Simultaneous algebraic reconstruction technique for up sampling, 101 number of classes (101-way classification) ranging from 0 to 100. Proposed system accuracy is evaluated using mean absolute error and with Pearson correlation coefficient that finds correlation between actual age and predicted age. Experimental results proved that data augmented Wide ResNet out performs the existing age prediction methods with 5% increase in accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

References

  1. Quividi, https://quividi.com/content-intelligence/. Last Accessed 15 Apr 2019

  2. Just how precise is Quividi’s gender classification?, https://quividi.com/how-precise-is-quividis-gender-classification/. Last Accessed 15 Apr 2019

  3. Chauhan NS (2019) Predict age and gender using convolutional neural network and openCV, https://towardsdatascience.com/predict-age-and-gender-using-convolutional-neural-network-and-opencv-fd90390e3ce6, Last Accessed 2 Jan 2019

  4. Ramos-Muguerza E, Docío-Fernández L, Alba-Castro JL (2018) From hard to soft biometrics through DNN transfer learning, 2018 IEEE 9th international conference on biometrics theory, applications and systems (BTAS), 2018, pp 1–7

  5. Sun Y, Lo FP, Lo B (2019) A deep learning approach on gender and age recognition using a single inertial sensor. In: 2019 IEEE 16th international conference on wearable and implantable body sensor networks (BSN), 2019, pp 1–4

  6. Neal TJ, Woodard DL. You are not acting like yourself: a study on soft biometric classification, person identification, and mobile device use. IEEE Trans Biometr, Behav, Identity Sci. 2019;1(2):109–22.

    Article  Google Scholar 

  7. Jiang M, Guo G. Body weight analysis from human body images. Trans Inf Forensics Secur. 2019;99:1–1.

    Google Scholar 

  8. Levi G, Hassner T (2015) Age and gender classification using convolutional neural networks. In: IEEE workshop on analysis and modeling of faces and gestures, 2015, p 1–9

  9. Agbo-Ajala O, Viriri S. Face-based age and gender classification using deep learning model. In: Dabrowski J, Rahman A, Paul M, editors. Image and video technology. PSIVT 2019. Lecture notes in computer science, vol. 11994. Cham: Springer; 2019.

    Google Scholar 

  10. Nwankpa C, Ijomah W, Gachagan A, Marshall S (2018) Activation functions: comparison of trends in practice and research for deep learning. arXiv Prepr. arXiv1811.03378

  11. Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks, in advances in neural information processing systems

  12. Zagoruyko S, Komodakis N (2016) Wide residual networks. In: Proceedings Br. Mach. Vis. Conf. 2016, May 2016, p. 87.1–87.12

  13. APPA-REAL (real and apparent age). http://chalearnlap.cvc.uab.es/dataset/26/description/ Last Accessed 2 Jan 2019

  14. Zhang H, Cisse M, Dauphin YN, Lopez-Paz D (2017) Mixup: beyond empirical risk minimization. In arXiv: 1710.09412

  15. https://github.com/yu4u/mixup-generator. Last Accessed 2 May 2019

  16. Kazemi V, Sullivan J (2014) One millisecond face alignment with an ensemble of regression trees. In: IEEE Conference on computer vision and pattern recognition, 2014, p 1867–1874

  17. Brown A, Mettes P, Worring M (2019) 4-Connected shift residual networks, ICCV Workshop 2019, p 1–8

  18. https://www.dlology.com/blog/easy-real-time-gender-age-prediction-from-webcam-video-with-keras/. Last Accessed 2 Jan 2019

  19. Bobrov E, Georgievskaya A, Kiselev K, Sevastopolsky A, Zhavoronkov A, Gurov S, Rudakov K, Tobar MD, Jaspers S, Clemann S. PhotoAgeClock: deep learning algorithms for development of non-invasive visual biomarkers of aging. Aging. 2018;10(11):3249–59. https://doi.org/10.18632/aging.101629.

    Article  Google Scholar 

  20. Biamby G, Fair D, Karapetov A, Karapetov B (2018) Age and gender classification using deep neural networks. https://medium.com/@andreykar_79244/age-and-gender-classification-using-deep-neural-networks-a8ded298a838. Last Accessed 2 Jan 2019

  21. Andersen AH, Kak AC. Simultaneous algebraic reconstruction technique (SART): a superior implementation of the ART algorithm. Ultrason Imaging. 1984;6(1):81–94.

    Article  Google Scholar 

  22. Vasavi S, Shaik R, Yarlagadda S. Moving object classification in a video sequence using invariant feature extraction. Hershey: IGI Global; 2018. p. 1–25.

    Google Scholar 

  23. Murphy K. Machine learning: a probabilistic perspective. Cambridge: MIT; 2012.

    MATH  Google Scholar 

  24. Agustsson E, Timofte R, Escalera S, Baro X, Guyon I, Rothe R (2017) Apparent and real age estimation in still images with deep residual regressors on APPA-REAL database. In: IEEE International conference on automatic face and gesture recognition (FG), 2017, p 1–8

  25. Clapes A, Bilici O, Temirova D, Avots E, Anbarjafari G, Escalera S (2019) From apparent to real age: gender, age, ethnic, makeup, and expression bias analysis in real age estimation CVPR conference, p 2486–2495

  26. Rondeau J, Alvarez M (2018) Deep modeling of human age guesses for apparent age estimation. In: International joint conference on neural networks (IJCNN), Rio de Janeiro, 2018, pp 01–08

  27. Gunjal A, Abin D. Survey on age estimation system. Int J Comput Appl. 2018;182(3):1–4.

    Google Scholar 

  28. Debgupta R, Chaudhuri BB, Tripathy BK. A wide resnet-based approach for age and gender estimation in face images. International Conference on innovative computing and communications. Advances in intelligent systems and Computing, vol. 1087. Singapore: Springer; 2020.

    Google Scholar 

  29. Deng Y, Luo P, Loy CC, Tang X (2014) Pedestrian attribute recognition at far distance. In: 22nd International conference on multimedia

Download references

Funding

Not applicable.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, VR Siddhartha Engineering College, Vijayawada, India

    S. Vasavi & P. Vineela

  2. Department of Space, Advanced Data Research Institute, Hyderabad, India

    S. Venkat Raman

Authors
  1. S. Vasavi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. P. Vineela
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. S. Venkat Raman
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to S. Vasavi.

Ethics declarations

Conflict of interest

Authors have no conflicts of interest.

Ethics approval

Ethics approval was not required for this study.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the topical collection “Data Science and Communication” guest edited by Kamesh Namudri, Naveen Chilamkurti, Sushma S. J. and S. Padmashree.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vasavi, S., Vineela, P. & Raman, S.V. Age Detection in a Surveillance Video Using Deep Learning Technique. SN COMPUT. SCI. 2, 249 (2021). https://doi.org/10.1007/s42979-021-00620-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-021-00620-w

Keywords

Search

Navigation