Ensemble of shallow convolutional neural networks for classification of gender in video stream

Article Sidebar

PDF (Українська)
DOI: https://doi.org/10.20998/2522-9052.2019.4.11
Keywords:
ensemble, shallow neural networks, face detection, gender classification, image recognition, convolutional neural networks, trusted voting, aggregation, frame, video stream

Main Article Content

Oleksii Gorokhovatskyi
Kharkiv National University of Radio Electronics, Kharkiv
https://orcid.org/0000-0003-3477-2132
Olena Peredrii
Kharkiv National University of Radio Electronics, Kharkiv
https://orcid.org/0000-0003-0390-1931

Abstract

Subjects of the research are neural network models for a person’s gender classification by the image of a person when processing a video stream. The goal is to investigate the effectiveness of individual shallow neural networks and ensembles created from them to solve the problem of classifying a person’s gender in a video stream, which is processed as a sequence of individual frames. Tasks include the development of mathematical models to process a sequence of frames with accumulation using different strategies, investigation of their effectiveness for solving the classification problem, compiling ensembles of shallow convolutional neural networks. Following methods are used: neural networks modeling, data mining, mathematical statistics, functional analysis, computer modeling. Results follows: it is shown that the classification accuracy can be improved both through the use of different voting models of the individual frames classification results, and through the use of ensembles of shallow convolutional neural networks. The insignificant hardware and software resources that are required for their training and use make it possible to increase the classification speed by several times in comparison with the results of classification by neural networks, that have more complex architecture. Conclusions. The contribution is in  the creation of ensembles of shallow neural networks, the general decision in which is made after the generalization by various voting methods with confidence both the classification results of individual frames and the classification results of the same frame by different networks, which makes it possible to increase the accuracy and speed of classification. The practical significance of the work is in the creation of a method that makes it possible to provide an acceptable classification accuracy and significantly improve performance by using shallow neural network architectures.

Article Details

How to Cite
Gorokhovatskyi, O., & Peredrii, O. (2019). Ensemble of shallow convolutional neural networks for classification of gender in video stream. Advanced Information Systems, 3(4), 74–79. https://doi.org/10.20998/2522-9052.2019.4.11
Issue
Vol. 3 No. 4 (2019): Advanced Information Systems
Section
Intelligent information systems
Author Biographies

Oleksii Gorokhovatskyi, Kharkiv National University of Radio Electronics, Kharkiv

Candidate of Technical Sciences, Associate Professor, Associate Professor of Computer Science and Computer Engineering Department

Olena Peredrii, Kharkiv National University of Radio Electronics, Kharkiv

Candidate of Technical Sciences, Senior Lecturer of Computer Science and Computer Engineering Department

References

Dehghan, A., Ortiz, E.G., Shu, G. and Masood, S.Z. (2017), DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Networks, available at: https://arxiv.org/pdf/1702. 04280.pdf.

El Khiyari, H., Wechsler, H. (2016), Face Verification Subject to Varying (Age, Ethnicity, and Gender) Demographics Using Deep Learning, DOI: https://doi.org/10.4172/2155-6180.1000323

Levi, G. and Hassner, T. (2015), “Age and Gender Classification Using Convolutional Neural Networks”, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, DOI: https://doi.org/10.1109/cvprw.2015.7301352.

Rothe, R., Timofte, R. and Gool, L.V. (2015), “Dex: Deep expectation of apparent age from a single image”, Proceedings of the IEEE International Conference on Computer Vision Workshop (ICCVW), DOI: https://doi.org/10.1109/iccvw.2015.41.

Simonyan, K. and Zisserman, A. (2015), Very deep convolutional networks for large-scale image recognition, available at: https://arxiv.org /pdf/1409.1556.pdf.

Ekmekji, A. (2016), Convolutional Neural Networks for Age and Gender Classification, available at:

http://cs231n.stanford.edu/reports/2016/ pdfs/003_Report.pdf.

Gorokhovatskyi, O. (2018), “Shallow Convolutional Neural Networks for Pattern Recognition Problems”, Proceedings of the IEEE International Conference on DataStream Mining & Processing, 23-27 August 2018, Lviv, Ukraine, pp. 459-463, DOI: https://doi.org/10.1109/dsmp.2018.8478540.

Hebda, B. and Kryjak, T. (2016), “A compact deep convolutional neural network architecture for video based age and gender estimation”, Proceedings of the Federated Conference on Computer Science and Information Systems, pp. 787–790.

Hogervorst, J., Okafor, E. and Wiering, M. (2017), Deep Colorization for Facial Gender Recognition, available at: http://www.ai.rug.nl/ ~mwiering/GROUP/ARTICLES/Facial_Gender_Classification.pdf.

Antipov, G., Berrani, S. and Dugelay, J. (2016), “Minimalistic CNN-based ensemble model for gender prediction from face image”, Pattern Recognition Letters, Vol. 70, Issue C, pp. 59-65, DOI: 10.1016/j.patrec.2015.11.011.

Jia, S., Lansdall-Welfare, T. and Cristianin, N. (2016), Gender Classification by Deep Learning on Millions of Weakly Labelled Images, available at: http://www.lansdall-welfare.com/wp-content/uploads/2016/11/deep_gender.pdf.

Selim, M., Sundararajan, S., Pagani, A. and Stricker, D. (2018), Image Quality-Aware Deep Networks Ensemble for Efficient Gender Recognition in the Wild, available at: http://av.dfki.de/ ~pagani/papers/Selim2018_VISAPP.pdf.

Bekios-Calfa, J., Buenaposada, J. M. and Baumela, L. (2011), “Revisiting Linear Discriminant Techniques in Gender Recogni-tion”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 4, pp. 858-864, DOI: https://doi.org/10.1109/tpami.2010.208.

Demirkus, M., Toews, M., Clark, J. J. and Arbel, T. (2010), “Gender classification from unconstrained video sequences”, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Workshops. DOI: https://doi.org/10.1109/cvprw.2010.5543829.

Huang, G. B., Mattar, M., Lee, H. and Learned-Miller, E. (2012), “Learning to Align from Scratch”, Advances in Neural In-formation Processing Systems, pp. 764-772.

Huang, G. B., Ramesh, M., Berg, T. and Learned-Miller, E. (2007), Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments, University of Massachusetts, Amherst, Technical Report 07-49.

Viola, P. and Jones, M. (2001), “Rapid object detection using a boosted cascade of simple features”, Proceeding of the Interna-tional Conference on Computer Vision and Pattern Recognition , vol. 1, pp. 511-518.

OpenCV Open Source Computer Vision, available at: https://docs.opencv.org/master/index.html.

Liu, Z., Luo, P., Wang, X. and Tang, X. (2015), “Deep Learning Face Attributes in the Wild”, Proceedings of International Conference on Computer Vision (ICCV), DOI: https://doi.org/10.1109/iccv.2015.425.

Eidinger, E., Enbar, R. and Hassner, T. (2014), “Age and gender estimation of unfiltered faces”, IEEE Transactions on infor-mation forensics and security, Vol. 9, Issue 12, DOI:.1109/tifs.2014.2359646.

Easy Real time gender age prediction from webcam video with Keras (2017), available at:

https://github.com/Tony607/Keras_age_gender.

Zagoruyko, S. and Komodakis, N. (2017), Wide Residual Networks, available at:

https://arxiv.org/pdf/1605.07146.pdf.

Shu, C. and Burn, D. H. (2004), “Artificial neural network ensembles and their application in pooled flood frequency analysis”, Water Resources Research, Vol. 40, W09301, DOI: https://doi.org/10.1029/2003WR002816.

Frazao, X., Alexandre, L. A. (2014), Weighted Convolutional Neural Network Ensemble, available at:

https://www.di.ubi.pt/~lfbaa/ pubs/ciarp2014.pdf.

Jiḿenez, D. (1998), “Dynamically Weighted Ensemble Neural Networks for Classification”, Proceedings of the IEEE Interna-tional Joint Conference on Neural Networks, DOI: https://doi.org/10.1109/ijcnn.1998.682375.

Ju, C., Bibaut, A. and Van der Laan, M.J. (2017), “The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image Classification”, Journal of Applied Statistics, 45(15), DOI:

https://doi.org/10.1080/02664763.2018.1441383.